About

About Spot

Spot uses articulated legs to climb stairs, cross uneven ground and position sensors around industrial equipment. Its autonomy stack supports mapped patrols, obstacle avoidance and repeatable data capture, with remote operation available for hazardous or unfamiliar areas. Spot Arm adds mobile manipulation and equipment interaction.

Thermal cameras, acoustic imagers, gas sensors, lidar and other payloads connect through mechanical, electrical and software interfaces. Orbit software schedules missions, manages fleets and associates readings with facility assets. Spot is deployed across energy, manufacturing, construction, public safety and research organisations.

Capabilities

Source-backed capabilities

Capability areas: Autonomous navigation
Workflows: Industrial inspection
Operating environments: Industrial facility
Target markets: Infrastructure operators, energy companies, construction firms and industrial inspection teams.
Deployment model: Commercial product with broad deployment across multiple industries and geographies.
Multi-terrain locomotion
Research demonstration - 2026-04-15 - The CART paper introduces context-aware terrain adaptation using temporal sequence selection for legged robots.
Source
Navigation and obstacle avoidance
Research demonstration - 2026-04-03 - The paper compares expressive motion, lights, text, and audio as communication modalities for robot navigation intent.
Source
Navigation and obstacle avoidance
Research demonstration - 2026-02-23 - Hilbert-augmented RL paper validates multi-robot coverage trajectories on Spot
Source
Multi-terrain locomotion
Research demonstration - 2025-08-22 - The work gives Spot a benchmark for traversability-aware terrain classification using onboard robot state.
Source
Obstacle-course traversal
Research demonstration - 2025-08-22 - The work gives Spot a benchmark for traversability-aware terrain classification using onboard robot state.
Source
Navigation and obstacle avoidance
Claimed - Boston Dynamics reports more than 1,500 Spot robots in customer hands and presents the product for repeatable autonomous inspection, site mapping and obstacle-aware mobility.
Source
Semantic scene understanding
Research demonstration - 2026-06-22 - The authors demonstrate downstream robotics use in an open-vocabulary object-retrieval task using a real-world indoor deployment on Boston Dynamics Spot.
Source
Semantic scene understanding
Research demonstration - 2026-03-30 - Pandora builds articulated 3D scene graphs from egocentric vision to enrich robot scene representations.
Source
SLAM mapping
Claimed - Boston Dynamics reports more than 1,500 Spot robots in customer hands and presents the product for repeatable autonomous inspection, site mapping and obstacle-aware mobility.
Source
Object retrieval
Research demonstration - 2026-06-22 - 3D semantic scene-graph paper demonstrates open-vocabulary object retrieval on Spot
Source
Whole-body loco-manipulation
Research demonstration - 2025-01-17 - By combining the agility of legged locomotion with the capabilities of manipulation, loco-manipulation platforms have the potential to perform complex tasks in real-world applications.
Source
Remote and shared control
Pilot - 2025-03-18 - Boston Dynamics' Spot Deployed for Remote Operations at Sellafield
Source
Remote and shared control
Research demonstration - 2020-10-19 - The work gives Spot an early high-signal benchmark for complex autonomous missions beyond teleoperated inspection.
Source
Robotic inspection
Commercial deployment - Boston Dynamics reports more than 1,500 Spot robots in customer hands and presents the product for repeatable autonomous inspection, site mapping and obstacle-aware mobility.
Source
Robotic inspection
Customer-site use - 2026-07-08 - Coca-Cola Europacific Partners uses Spot at its Barcelona production site for hourly autonomous inspections after roughly 18–24 months of site use reported in the case study.
Source
Search and rescue
Customer-site use - 2026-02-06 - This equipment was deployed to assist in public safety incidents such as law enforcement activities, fire response, and search and rescue operations.
Source
Robotic inspection
Customer-site use - 2025-11-17 - Spot performed approximately 10,000 autonomous inspections per week, capturing thermal, acoustic, and visual data across rapeseed and sun.
Source
Robotic inspection
Customer-site use - 2025-06-17 - Cargill’s Amsterdam Multiseed plant has run a Spot pilot since mid-2024; autonomous inspection missions last about two hours and include hourly scans at selected assets.
Source
Robotic inspection
Customer-site use - 2024-07-01 - Novo Nordisk’s January 2024 Spot pilot mapped roughly 300 inspection points for autonomous inspection work in a pharmaceutical production environment.
Source
Fire-aware navigation
Research demonstration - 2026-02-22 - The paper builds real-time thermal radiation fields from registered depth and thermal images for mobile robot navigation near fire.
Source
Inspection
Research demonstration - 2026-02-18 - The paper combines supervised failure classification and anomaly detection for autonomous inspection tasks.
Source
Robotic inspection
Research demonstration - 2026-02-18 - The paper combines supervised failure classification and anomaly detection for autonomous inspection tasks.
Source

Operations

Operating Milestone
hourly inspections - 2026-07-08 - Coca-Cola Europacific Partners Barcelona - Coca-Cola Europacific Partners uses Spot at its Barcelona production site for hourly autonomous inspections after roughly 18–24 months of site use reported in the case study.
Source
Operating Milestone
complete culvert scan in under 10 minutes - 2026-04-08 - Caltrans Northern California - Caltrans used Spot to scan a damaged highway culvert in under ten minutes and later deployed it for a bridge-soffit inspection; the case reports more than $50,000 in avoided costs.
Source
Operating Milestone
routine factory data capture and inspection - 2026-02-18 - ST Engineering MRAS factory - ST Engineering MRAS uses Spot for routine factory data capture and inspection to support digital-twin and maintenance workflows.
Source
Operating Milestone
six trained Spot operators - 2026-02-11 - Oswego County Sheriff’s Office - Oswego County added Spot to its emergency-response robotics fleet and trained six sheriff’s deputies as drone pilots and Spot operators.
Source
Operating Milestone
39 leaks in the first month - 2026-01-26 - ZF Active Safety France - Automotive braking-system manufacturing plant - At ZF Active Safety France’s Bouzonville plant, configured Spot inspections found 39 compressed-air leaks during the first month, a result attributed to plant manager Lionel Champlon.
Source
Operating Milestone
2-hour autonomous missions - 2025-06-17 - Cargill Amsterdam Multiseed - Cargill’s Amsterdam Multiseed plant has run a Spot pilot since mid-2024; autonomous inspection missions last about two hours and include hourly scans at selected assets.
Source
Operating Milestone
188 measurement points - 2025-05-08 - J-POWER Onikobe Geothermal Power Plant - J-POWER introduced Spot at Onikobe in 2022 for smart maintenance; the disclosed programme runs six missions covering 188 measurement points.
Source
Operating Milestone
about 40 actions per mission - 2025-04-07 - POSCO Gwangyang Steelworks - POSCO has used Spot for blast-furnace inspection since 2023; it runs two Autowalk missions multiple times a day, with about 40 thermal-camera actions per mission.
Source
Operating Milestone
recurring day-and-night inspections - 2025-02-25 - Ash Grove Cement Seattle - Ash Grove Cement deployed Spot at its Seattle plant for recurring day-and-night equipment inspections in an operating cement-manufacturing environment.
Source
Operating Milestone
about 700 assets per mission - 2024-10-23 - Michelin US5 Lexington - Michelin’s US5 plant runs seven Spot inspection missions covering about 700 assets per mission; the programme generated 72 work orders and identified 66 air leaks.
Source
Operating Milestone
300 inspection points - 2024-07-01 - Novo Nordisk production site - Novo Nordisk’s January 2024 Spot pilot mapped roughly 300 inspection points for autonomous inspection work in a pharmaceutical production environment.
Source
Operating Milestone
Spot acquired for automated factory inspections in 2023 - 2024-07-01 - BMW Group Plant Hams Hall - BMW Group Plant Hams Hall acquired Spot in 2023 for automated inspections that feed data into the plant’s digital twin, alongside ad-hoc production-line measurements.
Source
Operating Milestone
daily inspections - 2024-02-20 - Chevron Bakersfield cogeneration facility - After proof-of-concept work, Chevron moved Spot into a production role at its Bakersfield cogeneration facility for daily inspections; its fleet also expanded to two named refineries in summer 2023.
Source
Operating Milestone
1,800 inspections per week - 2024-01-10 - AB InBev Leuven brewery - Spot conducts 1,800 inspections each week across ten packaging lines at AB InBev’s Leuven brewery; in its first six months it found nearly 150 anomalies and reduced average repair time to 13 days.
Source
Operating Milestone
60 thermal-image points - 2023-12-12 - Southern Power Plant Wansley - Southern Company piloted Spot at Plant Wansley in fall 2022; one HRSG route captured thermal images at 60 points and sent results into its asset-management workflow.
Source
Operating Milestone
30+ autonomous missions - 2023-10-30 - Nestlé Purina factory - Nestlé Purina deployed Spot for recurring thermal and acoustic packaging-line inspections; the case study reports more than 30 programmed missions, including routes that run hourly.
Source
Operating Milestone
routine autonomous visual and thermal inspections - 2023-10-10 - Woodside Energy Pluto LNG - Woodside launched its Spector data-capture service at Pluto LNG, using Spot for routine autonomous visual and thermal inspections linked to the FUSE digital twin.
Source
Operating Milestone
one manual energized-hall inspection every two weeks - 2023-07-10 - National Grid Sandy Pond Converter Station - By July 2023, National Grid had moved Spot from pilot work into regular production inspections at Sandy Pond, including autonomous grounds missions and a manual energized-hall mission every two weeks.
Source
Operating Milestone
daily autonomous overnight reality capture - 2023-04-11 - Turner Construction data-centre projects - Turner Construction used Spot with DroneDeploy and an Insta360 camera for autonomous overnight reality capture on large data-centre construction sites, scheduled to repeat daily.
Source
Operating Milestone
Spot integrated into inspection process - 2023-03-29 - RATP Paris Métro - RATP integrated its Spot robot, Perceval, into the inspection process for difficult-to-access Paris Métro infrastructure.
Source
Operating Milestone
thousands of inspection points - 2023-01-04 - GlobalFoundries Burlington - GlobalFoundries uses Spot with Levatas for autonomous predictive-maintenance missions spanning thousands of inspection points at its Burlington semiconductor facility.
Source
Operating Milestone
nuclear-site inspection pilot - 2022-10-19 - Dominion Energy - Dominion Energy evaluated Spot for remote inspection work at a nuclear-energy site; the fact is retained as a historical pilot, not an active fleet claim.
Source
Operating Milestone
mine-research pilot begun in 2020 - 2022-10-12 - LKAB and Luleå University of Technology - LKAB and Luleå University of Technology used Spot in a mine-research pilot begun in 2020; the row records the bounded historical field programme.
Source

Deployments

Operating Use
14 Spot units operating - 2026-08-30 - Intel Foundry - Semiconductor-fab inspections - Fourteen Boston Dynamics Spot units operate across six Intel Foundry facilities; a target of 30 units is forward-looking and excluded from the deployed count.
Source

Observed use

Exact-product configurations are shown without inferring supply, purchase, customer status, standard fit, deployment or partnership.

NXP Attention Front End
2026-05-19 - Evaluation - Connected - Physical - NXP showed its Attention Front End integrated on a Boston Dynamics Spot while evaluating multimodal conversational AI at the edge.
Source
Scanner and camera system (exact models unspecified)
Pilot - Mounted - Physical - Roboverse Reply mounted scanners and cameras on Spot to capture the warehouse used for Otto Group’s pilot digital twin.
Source
Observed configuration
Research Experiment - Tested With - Physical - FCTS evaluates a physical Boston Dynamics Spot using RealSense D435i depth observations.
Source
Leica BLK ARC
Reference Design - Mounted - Physical - Leica BLK ARC is a commercial autonomous scanning payload designed to mount on and operate with Boston Dynamics Spot.
Source

Supply

Supply / Components

Spot
Field Foundation Models - software - Field AI - FieldAI supplies Field Foundation Models integrated with Spot for autonomous construction-site operations - source: bostondynamics.com
Source
Spot
Rajant Kinetic Mesh Radio Kit For Spot - Communications - Rajant Corporation - Boston Dynamics offers the Rajant Kinetic Mesh Radio Kit as an optional Spot communications payload - source: bostondynamics.com
Source

Research

FCTS: Failure-Guided Curriculum Tree Search Over Generated Terrain for Legged Parkour
2026-10-15 - Research Publication - FCTS generates terrain curricula from localised policy failures and searches competing training trajectories under a fixed budget. Evaluation uses reconstructed construction-site geometry and a physical Boston Dynamics Spot parkour course.
Source
BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation
2026-10-09 - Research Publication - BT-Agent combines language-model task reasoning with predefined behavior-tree skills and local execution guards. A9B model runs onboard Boston Dynamics Spot with Jetson Thor, completing11 of15 research trials with operator-approved motion. The paper introduces a161-task text benchmark and39 Habitat evaluations; implementation and benchmark code are planned releases.
Source
Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection
2026-07-17 - Research Publication - Spot collects indoor views for annotation-efficient object-detection training.
Source
From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models
2026-06-22 - Research Publication - Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level.
Source
Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning
2026-05-08 - Research Publication - Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation.
Source
Simulation and Motion Control of the Spot Quadruped Robot in a Webots Virtual Environment: An Approach for Locomotion Algorithm Validation
2026-04-17 - Research Publication - This work presents a control implementation for the Boston Dynamics Spot quadruped robot in the Webots simulation environment. The main objective was to develop and validate fundamental motion control algorithms, including rest postures, state transitions, and complex movements such as the greeting gesture (“give paw”). The methodology employed is based on the decomposition of movements into smooth trajectories between target positions, using temporal linear interpolation to ensure natural transitions. The results obtained demonstrate the effectiveness of the proposed approach for simulating quadruped robot behaviors, providing a foundation for the development of more complex navigation and manipulation algorithms. The implementation produces stable and realistic movements, validating the use of Webots as a development platform for quadruped robotics. The contributions of this work inclu
Source
CART: Context-Aware Terrain Adaptation using Temporal Sequence Selection for Legged Robots
2026-04-15 - Research Publication - Animals in nature combine multiple modalities, such as sight and feel, to perceive terrain and develop an understanding of how to walk on uneven terrain in an efficient manner.
Source
Google DeepMind releases Gemini Robotics-ER 1.6 embodied reasoning model
2026-04-14 - Research Publication - Google DeepMind released Gemini Robotics-ER 1.6, an embodied reasoning model for spatial understanding, planning, success detection, and instrument reading. The post highlights Boston Dynamics Spot as a partner context for industrial gauge-reading tasks.
Source
Boston Dynamics demonstrates Spot task execution with Gemini Robotics
2026-04-14 - Research Publication - Boston Dynamics demonstrates Spot using Gemini Robotics-ER 1.5 to interpret a home environment, select useful robot tools, and call Spot SDK functions. The demo makes Spot the explicit platform context for embodied reasoning and robot-tool use.
Source
Toward Hardware-Agnostic Quadrupedal World Models via Morphology Conditioning
2026-04-09 - Research Publication - World models promise a paradigm shift in robotics, where an agent learns the underlying physics of its environment once to enable efficient planning and behavior learning.
Source
Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
2026-04-09 - Research Publication - This paper presents a sim-to-real approach that enables legged robots to dynamically manipulate large and heavy objects with whole-body dexterity. Our key insight is that by performing test-time steering of a pre-trained whole-body control policy with a sample-based planner, we can enable these robots to solve a variety of dynamic loco-manipulation tasks.
Source
Boston Dynamics adds Gemini Robotics to Orbit AIVI-Learning for Spot
2026-04-08 - Research Publication - Boston Dynamics describes Orbit AIVI-Learning powered by Gemini and Gemini Robotics-ER 1.6 for industrial inspection. The source ties Spot to facility understanding, gauge interpretation, and repeated learning from deployed inspection tasks.
Source
Do Robots Need Body Language? Comparing Communication Modalities for Legible Motion Intent in Human-Shared Spaces
2026-04-03 - Research Publication - Robots in shared spaces often move in ways that are difficult for people to interpret, placing the burden on humans to adapt.
Source
Pandora: Articulated 3D Scene Graphs from Egocentric Vision
2026-03-30 - Research Publication - Robotic mapping systems typically approach building metric-semantic scene representations from the robot's own sensors and cameras.
Source
MEVIUS2: Practical Open-Source Quadruped Robot with Sheet Metal Welding and Multimodal Perception
2026-03-23 - Research Publication - Various quadruped robots have been developed to date, and thanks to reinforcement learning, they are now capable of traversing diverse types of rough terrain. In parallel, there is a growing trend of releasing these robot designs as open-source, enabling researchers to freely build and modify robots themselves.
Source
Efficient Autonomous Navigation of a Quadruped Robot in Underground Mines on Edge Hardware
2026-03-04 - Research Publication - A configured Spot performs fully autonomous navigation in an experimental underground mine.
Source
Hilbert-Augmented Reinforcement Learning for Scalable Multi-Robot Coverage and Exploration
2026-02-23 - Research Publication - We present a coverage framework that integrates Hilbert space-filling priors into decentralized multi-robot learning and execution.
Source
Understanding Fire Through Thermal Radiation Fields for Mobile Robots
2026-02-22 - Research Publication - Safely moving through environments affected by fire is a critical capability for autonomous mobile robots deployed in disaster response.
Source
World Model Failure Classification and Anomaly Detection for Autonomous Inspection
2026-02-18 - Research Publication - Autonomous inspection robots for monitoring industrial sites can reduce costs and risks associated with human-led inspection.
Source
ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control
2026-01-30 - Research Publication - Physical Atlas and Spot execute diverse zero-shot athletic motion skills.
Source
Heterogeneous Robot Collaboration in Unstructured Environments with Grounded Generative Intelligence
2025-10-30 - Research Publication - Heterogeneous robot teams operating in realistic settings often must accomplish complex missions requiring collaboration and adaptation to information acquired online.
Source
DIV-Nav: Open-Vocabulary Spatial Relationships for Multi-Object Navigation
2025-10-18 - Research Publication - Advances in open-vocabulary semantic mapping and object navigation have enabled robots to perform an informed search of their environment for an arbitrary object.
Source
Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis
2025-10-09 - Research Publication - Developing table tennis robots that mirror human speed, accuracy, and ability to predict and respond to the full range of ball spins remains a significant challenge for legged robots. To demonstrate these capabilities we present a system to play dynamic table tennis for quadrupedal robots that integrates high speed perception, trajectory prediction, and agile control. Our system uses external cameras for high-speed ball localization, physical models with learned residuals to infer spin and predict trajectories, and a novel model predictive control (MPC) formulation for agile full-body control. Notably, a continuous set of stroke strategies emerge automatically from different ball return objectives using this control paradigm. We demonstrate our system in the real world on a Spot quadruped, evaluate accuracy of each system component, and exhibit coordination through the system's ability t
Source
Terrain Classification for the Spot Quadrupedal Mobile Robot Using Only Proprioceptive Sensing
2025-08-22 - Research Publication - Quadrupedal mobile robots can traverse a wider range of terrain types than their wheeled counterparts but do not perform the same on all terrain types.
Source
Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors
2025-08-18 - Research Publication - Mobile manipulation in dynamic environments is challenging due to movable obstacles blocking the robot's path.
Source
UniTac: Whole-Robot Touch Sensing Without Tactile Sensors
2025-07-10 - Research Publication - Robots can better interact with humans and unstructured environments through touch sensing. However, most commercial robots are not equipped with tactile skins, making it challenging to achieve even basic touch-sensing functions, such as contact localization. We present UniTac, a data-driven whole-body touch-sensing approach that uses only proprioceptive joint sensors and does not require the installation of additional sensors. Our approach enables a robot equipped solely with joint sensors to localize contacts. Our goal is to democratize touch sensing and provide an off-the-shelf tool for HRI researchers to provide their robots with touch-sensing capabilities. We validate our approach on two platforms: the Franka robot arm and the Spot quadruped. On Franka, we can localize contact to within 8.0 centimeters, and on Spot, we can localize to within 7.2 centimeters at around 2,000 Hz on an
Source
VISTA: Open-Vocabulary, Task-Relevant Robot Exploration with Online Semantic Gaussian Splatting
2025-07-01 - Research Publication - We present VISTA (Viewpoint-based Image selection with Semantic Task Awareness), an active exploration method for robots to plan informative trajectories that improve 3D map quality in areas most relevant for task completion. Given an open-vocabulary search instruction (e.
Source
A Spatial Relationship Aware Dataset for Robotics
2025-06-14 - Research Publication - Robotic task planning in real-world environments requires not only object recognition but also a nuanced understanding of spatial relationships between objects.
Source
High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measures
2025-04-24 - Research Publication - This work presents an overview of the technical details behind a high performance reinforcement learning policy deployment with the Spot RL Researcher Development Kit for low level motor access on Boston Dynamics Spot.
Source
A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications
2025-02-21 - Research Publication - Reinforcement learning (RL) has gained traction for its success in solving complex tasks for robotic applications.
Source
aliy98/immersive-spot-teleoperation
2025-01-22 - Research Publication - This repository contains a modular software architecture designed for immersive teleoperation of the Boston Dynamics Spot robot using the Meta Quest 2.
Source
SaadIqbalEE/Shoveling-earth-with-the-Boston-Dynamics-Spot-robot
2025-01-21 - Research Publication - Shoveling earth with the Boston Dynamics Spot robot
Source
Learning More With Less: Sample Efficient Model-Based RL for Loco-Manipulation
2025-01-17 - Research Publication - By combining the agility of legged locomotion with the capabilities of manipulation, loco-manipulation platforms have the potential to perform complex tasks in real-world applications.
Source
An Actionable Hierarchical Scene Representation Enhancing Autonomous Inspection Missions in Unknown Environments
2024-12-27 - Research Publication - In this article, we present the Layered Semantic Graphs (LSG), a novel actionable hierarchical scene graph, fully integrated with a multi-modal mission planner, the FLIE: A First-Look based Inspection and Exploration planner.
Source
DTAA: A Detect, Track and Avoid Architecture for navigation in spaces with Multiple Velocity Objects
2024-12-11 - Research Publication - Proactive collision avoidance measures are imperative in environments where humans and robots coexist.
Source
Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation
2024-11-12 - Research Publication - LIFGIF combines language-inferred map priors with established SLAM and navigation components for zero-shot instruction following.
Source
Physically-Consistent Parameter Identification of Robots in Contact
2024-09-15 - Research Publication - Accurate inertial parameter identification is crucial for the simulation and control of robots encountering intermittent contact with the environment. Classically, robots' inertial parameters are obtained from CAD models that are not precise (and sometimes not available, e.
Source
ReMoBot: Retrieval-Based Few-Shot Imitation Learning for Mobile Manipulation with Vision Foundation Models
2024-08-28 - Research Publication - Imitation learning (IL) algorithms typically distill demonstrations into parametric policies to mimic expert behavior.
Source
Benned-H/spot_skills
2024-08-20 - Research Publication - Motion-planning-based skills for Boston Dynamics' Spot robot
Source
Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs
2024-08-12 - Research Publication - Large Language Models (LLMs) have demonstrated remarkable abilities in various language tasks, making them promising candidates for decision-making in robotics.
Source
IntentionNet: Map-Lite Visual Navigation at the Kilometre Scale
2024-07-03 - Research Publication - This work explores the challenges of creating a scalable and robust robot navigation system that can traverse both indoor and outdoor environments to reach distant goals.
Source
Toward Autonomous Construction Material Inventory Management using a Boston Dynamics SPOT and Ultra-High Frequency (UHF) Passive RFID
2024-05-26 - Research Publication - Construction materials account for a significant percentage of the resources on a construction site and plays a vital role in the success of the project. By utilizing an experimental methodology, the goal of this research was to execute a proof of concept for autonomous inventory management of construction materials using Ultra-High Frequency passive RFID and a terrestrial autonomous robot. An experiment was administered to identify the reliability (tags read vs. tags placed) of the proposed system in a dynamic environment in autonomous mode. According to the results, the robot was largely able to navigate around and between smaller objects versus larger obstacles. Using Bootstrap simulation, the successful read rate (percent) was found to be [67,88] [LL, UL] at a 95 percent confidence interval. Based on the results, using a Boston Dynamics SPOT with UHF Passive RFID to control building
Source
AutoInspect: Towards Long-Term Autonomous Industrial Inspection
2024-04-19 - Research Publication - We give an overview of AutoInspect, a ROS-based software system for robust and extensible mission-level autonomy.
Source
Human Stress Response and Perceived Safety during Encounters with Quadruped Robots
2024-03-25 - Research Publication - Despite the rise of mobile robot deployments in home and work settings, perceived safety of users and bystanders is understudied in the human-robot interaction (HRI) literature.
Source
HARPER dataset paper studies human-pose forecasting from Boston Dynamics Spot
2024-03-21 - Research Publication - We introduce HARPER, a novel dataset for 3D body pose estimation and forecast in dyadic interactions between users and Spot, the quadruped robot manufactured by Boston Dynamics.
Source
sandialabs/spot_bt_ros
2024-03-14 - Research Publication - Behavior Tree ROS 2 package for Boston Dynamics' Spot robot.
Source
Safe Spot: Perceived safety of dominant and submissive appearances of quadruped robots in human-robot interactions
2024-03-08 - Research Publication - Unprecedented possibilities of quadruped robots have driven much research on the technical aspects of these robots.
Source
VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation
2023-12-06 - Research Publication - Understanding how humans leverage semantic knowledge to navigate unfamiliar environments and decide where to explore next is pivotal for developing robots capable of human-like search behaviors.
Source
ViT-A*: Legged Robot Path Planning using Vision Transformer A*
2023-10-11 - Research Publication - The authors propose an approach that utilizes differentiable planners, allowing the learning of end-to-end global plans via a neural network for commanding quadruped robots.
Source
MTG: Mapless Trajectory Generator with Traversability Coverage for Outdoor Navigation
2023-09-15 - Research Publication - We present a novel learning-based trajectory generation algorithm for outdoor robot navigation.
Source
Language-Conditioned Observation Models for Visual Object Search
2023-09-13 - Research Publication - The authors empirically evaluate their method by comparing against a state-of-the-art object search algorithm in simulation, and demonstrate that planning with their observation model yields a significantly higher average task completion rate (from 0.46 to 0.66) and more efficient and quicker object search than with a fixed-noise model.
Source
Using Lidar Intensity for Robot Navigation
2023-09-13 - Research Publication - The authors present Multi-Layer Intensity Map, a novel 3D object representation for robot perception and autonomous navigation.
Source
Deadlock-free, Safe, and Decentralized Multi-Robot Navigation in Social Mini-Games via Discrete-Time Control Barrier Functions
2023-08-21 - Research Publication - We present an approach to ensure safe and deadlock-free navigation for decentralized multi-robot systems operating in constrained environments, including doorways and intersections.
Source
rai-opensource/vlfm
2023-07-04 - Research Publication - The repository provides code associated with the paper VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation (ICRA 2024)
Source
Assessment of the Utilization of Quadruped Robots in Pharmaceutical Research and Development Laboratories
2023-07-03 - Research Publication - Drug development is becoming more and more complex and resource-intensive.
Source
Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimization
2023-06-15 - Research Publication - This paper presents a fully decentralized approach for realtime non-cooperative multi-robot navigation in social mini-games, such as navigating through a narrow doorway or negotiating right of way at a corridor intersection.
Source
EgoSpot:Egocentric Multimodal Control for Hands-Free Mobile Manipulation
2023-06-04 - Research Publication - The authors propose a novel hands-free control framework for the Boston Dynamics Spot robot using the Microsoft HoloLens 2 mixed-reality headset.
Source
Integration of robotics in underground mining construction works
2023-04-12 - Research Publication - Since November 2021, Acciona has been testing the SPOT quadruped robot (Boston Dynamics’ Spot) in the underground mining site in Chile, with the main goal of reducing risks for human personnel while increasing process control and productivity. The following tasks are currently being performed by the robot: high precision scanning for section control, high precision scanning after applying shotcrete to perform quality control by measuring the thickness, thermal monitoring of the shotcrete to estimate setting level and early mechanical resistance, image acquisition of the tunnel face that allows generating a geologic report and robotic exploration of the tunnel after blasting, to identify misfired explosives. Acciona’s Robotics & Automation team has implemented several sensors over the robotic platform Spot: Leica’s RTC360 scanner, Leica’s BLK360 scanner and Teledyna’s GXM320 thermal camer
Source
ASC: Adaptive Skill Coordination for Robotic Mobile Manipulation
2023-04-01 - Research Publication - The authors present Adaptive Skill Coordination (ASC) -- an approach for accomplishing long-horizon tasks like mobile pick-and-place (i.e., navigating to an object, picking it, navigating to another location, and placing it).
Source
VERN: Vegetation-aware Robot Navigation in Dense Unstructured Outdoor Environments
2023-03-25 - Research Publication - The authors propose a novel method for autonomous legged robot navigation in densely vegetated environments with a variety of pliable/traversable and non-pliable/untraversable vegetation.
Source
Learning-and-Intelligent-Systems/lis-spot-utils
2023-03-15 - Research Publication - A number of helpful utilities for doing cool things with the Boston Dynamics Spot Robot!
Source
A System for Generalized 3D Multi-Object Search
2023-03-06 - Research Publication - The study building upon a recent theoretical framework that exploited the octree structure for representing belief in 3D, the authors present GenMOS (Generalized Multi-Object Search), the first general-purpose system for multi-object search (MOS) in a 3D region that is robot-independent and environment-agnostic.
Source
Evaluation of Lidar-based 3D SLAM algorithms in SubT environment
2023-02-27 - Research Publication - Autonomous navigation of robots in harsh and GPS denied subterranean (SubT) environments with lack of natural or poor illumination is a challenging task that fosters the development of algorithms for pose estimation and mapping.
Source
SOCRATES: Text-based Human Search and Approach using a Robot Dog
2023-02-10 - Research Publication - The study proposes a SOCratic model for Robots Approaching humans based on TExt System (SOCRATES) focusing on the human search and approach based on free-form textual description; the robot first searches for the target user, then the robot proceeds to approach in a human-friendly manner.
Source
A Flexible Framework for Virtual Omnidirectional Vision to Improve Operator Situation Awareness
2023-02-01 - Research Publication - The study presents a flexible framework for virtual projections to increase situation awareness based on a novel method to fuse multiple cameras mounted anywhere on the robot.
Source
Generalized Object Search
2023-01-24 - Research Publication - In support of this argument, I develop methods and systems for (multi-)object search in 3D environments under uncertainty due to limited field of view, occlusion, noisy, unreliable detectors, spatial correlations between objects, and possibly ambiguous spatial language (e.g., "The red car is behind Chase Bank").
Source
CAPE: Corrective Actions from Precondition Errors using Large Language Models
2022-11-17 - Research Publication - Extracting commonsense knowledge from a large language model (LLM) offers a path to designing intelligent robots. Existing approaches that leverage LLMs for planning are unable to recover when an action fails and often resort to retrying failed actions, without resolving the error's underlying cause. We propose a novel approach (CAPE) that attempts to propose corrective actions to resolve precondition errors during planning. CAPE improves the quality of generated plans by leveraging few-shot reasoning from action preconditions. Our approach enables embodied agents to execute more tasks than baseline methods while ensuring semantic correctness and minimizing re-prompting. In VirtualHome, CAPE generates executable plans while improving a human-annotated plan correctness metric from 28.89% to 49.63% over SayCan. Our improvements transfer to a Boston Dynamics Spot robot initialized with a se
Source
dehezhang2/ego-spot
2022-11-16 - Research Publication - A HoloLens 2 application that enables users (especially amputy people) to control the Boston Dynamics Spot robot’s movement and arm
Source
MURobotics/SpotBasePackage
2022-11-04 - Research Publication - Base library for controlling Boston Dynamics Spot robots programmatically
Source
facebookresearch/home-robot
2022-11-01 - Research Publication - Mobile manipulation research tools for roboticists
Source
narittt/spot-bvi
2022-10-05 - Research Publication - Adds greater accessibility to a Boston Dynamics Spot Robot for the Blind and Visually Impaired (BVI). Consists of a Swift/SwiftUI based natural language app to take BVI user voice commands and a python-based server to relay those commands to Spot.
Source
The Use of Boston Dynamics SPOT in Support of LiDAR Scanning on Active Construction Sites
2022-07-15 - Research Publication - The Use of Boston Dynamics SPOT in Support of LiDAR Scanning on Active Construction Sites Eric Wetzel, Junshan Liu, Tom Leathem and Anoop Sattineni Pages 86-92 (2022 Proceedings of the 39th ISARC, Bogotá, Colombia, ISBN 978-952-69524-2-0, ISSN 2413-5844) Abstract: With the recent commercial availability of autonomous mobility platforms, construction researchers have focused their attention to the application of advanced robotic tools on jobsites. One such mobility platform is Boston Dynamic's robot, "SPOT." The software development kit (SDK) enabled, quadruped robot has the infrastructure to attach interchangeable payloads including LiDAR (Light Detection And Ranging) scanners. Researchers have conducted a pilot study comparatively analyzing terrestrial LiDAR scans from a human-based tripod scan system and the scans executed by SPOT in both manual and autonomous modes. The research looke
Source
A Step Towards Automated Tool Tracking on Construction Sites: Boston Dynamics SPOT and RFID
2022-05-15 - Research Publication - Tool tracking and inventory management on a construction project is often more reactive than proactive. It is not that tools are not of value, but to larger firms, a certain comfort level exists with a loss to a relatively small line item, especially when compared to the resources that may be expended to track the tool inventory. With current market construction robotics serving a number of uses, testing multiple applications of autonomous robots creates more return for end-users. This research aims to execute a proof of concept for automated tool tracking using an autonomous robot and RFID technology. The research was carried out with three types of scans namely: Human held RFID reader; Robot mounted RFID reader in manual mode; Robot mounted RFID reader in autonomous mode. A total of 39 tools were tagged using passive UHF RFID tags and the study looked at the average cycle count time it
Source
mattmaring/SPOT-navigation
2022-02-10 - Research Publication - Command line control and data collection interface for Boston Dynamics Spot Robot
Source
Socially CompliAnt Navigation Dataset (SCAND)
2022-01-01 - Research Publication - Adds a dataset artifact for both Jackal and Spot social navigation research.
Source
naokiyokoyama/bd_spot_wrapper
2021-12-03 - Research Publication - Scripts for experimentation with Boston Dynamics Spot Robot
Source
yezhicheng99/spot_manipulator
2021-05-07 - Research Publication - Boston dynamics spot robot with open manipulator
Source
Autonomous Spot paper demonstrates long-range exploration in extreme environments
2020-10-19 - Research Publication - This paper serves as one of the first efforts to enable large-scale and long-duration autonomy using the Boston Dynamics Spot robot.
Source
heuristicus/spot_ros
2020-09-08 - Research Publication - ROS driver for controlling Boston Dynamics' Spot robot
Source

Resources

Media library

Spot thermal inspection
image · Boston Dynamics
Source
Spot in food and beverage operations
image · Boston Dynamics
Source
Spot fleet and industrial dock
image · Boston Dynamics
Source
Spot with lidar payload
image · Boston Dynamics
Source
Spot in emergency response
image · Boston Dynamics
Source
Spot on a construction site
image · Boston Dynamics
Source
Spot Arm in operation
image · Boston Dynamics
Source
Spot at Cargill
video · Boston Dynamics
Source

Official technical documents, developer references and supporting media for Spot. Generic product news and press releases are excluded.

Spot robot specifications
PDF · Base robot · Boston Dynamics
Source
Spot SDK: robot overview and specifications
WEB · SDK · Boston Dynamics
Source
Spot payload electrical interface
WEB · Payload integration · Boston Dynamics
Source
Spot and Site Hub security white paper
PDF · Security · Boston Dynamics
Source
Spot battery safety data sheets
WEB / PDF · Battery · Boston Dynamics
Source

Timeline

Boston Dynamics releases Spot & Orbit 5.2
2026-09-10 - Product Launch - The release adds software workflows connecting inspection data, enterprise systems and robot actions. Orbit 5.2 expands APIs and fleet-management tooling used to coordinate Spot deployments. This is a software release for the existing Spot and Orbit stack, not a new robot product.
Source
Boston Dynamics expands Createc reseller and technology partnership
2026-08-03 - Partnership - Createc became an authorised Boston Dynamics reseller and technology provider after more than six years of collaboration. The agreement grants Createc global nuclear-sector authorisation, UK industrial-market representation and enterprise asset-management coverage across the UK and Republic of Ireland. Createc uses Spot for autonomous inspections in nuclear and power environments, including hazardous or difficult-to-access areas.
Source
Mariana Minerals begins deploying Spot at Copper One
2026-07-22 - Deployment - Spot is intended to automate routine inspections and collect field data for Mariana Minerals’ software framework. The deployment is scoped to the Copper One facility near Moab, Utah. The rollout was in progress when announced; fleet size was not disclosed.
Source
Boston Dynamics and FieldAI Partner to Deploy Robots in Dynamic Environments
2026-03-12 - Partnership - Boston Dynamics and FieldAI announced a partnership to deploy robots in uncharted and dynamic environments. The collaboration integrates FieldAI's Field Foundation Models with Boston Dynamics' Spot robot. This integration enables Spot to autonomously operate in complex, real-world settings without prior maps or predefined routes.
Source
Oswego County Drone Program Deploys Boston Dynamics' Spot Robot
2026-02-06 - Deployment - The Oswego County Emergency Management Office received a $400 donation from Stewart's Shops in Minetto. The funds were allocated to purchase equipment for the county's drone and robotic program, including Boston Dynamics' Spot robot. This equipment was deployed to assist in public safety incidents such as law enforcement activities, fire response, and search and rescue operations.
Source
Boston Dynamics Spot inspects ZF’s Bouzonville plant with Intuitive Robots
2026-01-26 - Deployment - Plant manager Lionel Champlon credited the robot with detecting 39 compressed-air leaks in its first month. The configured robot reads gauges, checks filter status and performs thermal and acoustic inspections. Intuitive Robots handled site assessment, team training, AI adaptation and autonomous-mission implementation.
Source
Cargill deploys Boston Dynamics' Spot robot in Amsterdam
2025-11-17 - Deployment - Cargill introduced Boston Dynamics' four-legged robot, Spot, at its Amsterdam Multiseed crush and refinery plant. Spot performed approximately 10,000 autonomous inspections per week, capturing thermal, acoustic, and visual data across rapeseed and sun. The robot identified maintenance issues such as equipment overheating, product leaks, and ventilation faults, alerting operators before p.
Source
Boston Dynamics Spot performs daily inspections at Intel Foundry
2025-08-01 - Deployment - Intel Foundry uses Spot across six facilities for daily inspections, with 14 units operating and a target of 30; the robots navigate complex environments and stream inspection data to centralized monitoring systems. The quadrupeds carry RealSense depth cameras alongside thermal cameras, acoustic imagers and lidar to inspect operating fabs while reducing worker exposure and improving coverage. The case study says deployment began in June 2023 and that RealSense cameras support depth perception, hazard avoidance and remote livestreaming for global robot management.
Source
National Robotarium runs Spot research over private 5G
2025-07-30 - Research Publication - The research team had three Spot units, including an Enterprise model with a 5G-capable modem. A remote agricultural trial used Spot to collect crop images at sites kilometres from the control point. A separate project used a Meta Quest 3 interface to guide Spot through an outdoor industrial test area.
Source
Boston Dynamics' Spot Deployed for Remote Operations at Sellafield
2025-03-18 - Deployment - AtkinsRéalis and Sellafield Ltd successfully operated the Spot robot remotely from an off-site location. The trial demonstrated the potential for virtual site access on nuclear-licensed sites. Spot has been used to inspect areas, capture data, and perform tasks in hazardous environments at Sellafield.
Source
National Grid moves Spot into regular Sandy Pond inspections
2023-07-10 - Deployment - Spot traversed the property autonomously with an infrared camera to inspect equipment for hot spots. Operators also guided Spot through the energized thyristor hall once every two weeks. The production workflow increased access beyond the site’s former annual hall inspection and six-month infrared-check cadence.
Source
Boston Dynamics Releases Spot 3.3 with Enhanced Inspection Features
2023-06-20 - Product Launch - Spot 3.3 introduces new features and hardware to improve autonomous inspections. Enhancements include flexible autonomy, repeatable data capture, and enterprise integrations. The update aims to make inspection rounds safer and more efficient for customers.
Source
Boston Dynamics Deploys Spot Robots at Ontario Power Generation
2022-06-13 - Deployment - Ontario Power Generation (OPG) has deployed five Boston Dynamics Spot robots across various divisions. The robots assist in tasks such as inspections and research and development missions. OPG is collaborating with Boston Dynamics to establish an in-house maintenance program for the Spot fleet.
Source
FDNY Purchases Two Boston Dynamics Spot Robots for Search and Rescue
2022-03-19 - Commercial Order - The New York City Fire Department purchased two Spot robotic dogs from Boston Dynamics, each costing approximately $75,000. The 70-pound robots were acquired for use in hazardous materials situations and search and rescue operations. FDNY became the first fire department in the United States to acquire these robots.
Source
Spot selected for 2021 RBR50 Robotics Innovation Award
2021-06-30 - Award - Boston Dynamics' quadruped robot, Spot, was selected for the 2021 RBR50 Robotics Innovation Award. The award recognized Spot's innovative capabilities in the robotics field. The RBR50 list celebrates forward-thinking organizations and their impactful creations.
Source
NASA's NeBula enables Spot to explore Martian-like caves
2021-06-25 - Partnership - NASA's Jet Propulsion Laboratory (JPL) integrated its NeBula autonomy and AI system with Boston Dynamics' Spot robot. The combined system autonomously explored Martian-like caves on Earth without prior maps or human guidance. This demonstration showcased the robot's ability to navigate extreme terrains independently.
Source
BP Deploys Boston Dynamics' Spot Robot on Mad Dog Platform
2020-11-13 - Deployment - BP deployed Boston Dynamics' quadruped robot, Spot, on its Mad Dog platform in the Gulf of Mexico to enhance safety and operational efficiency. Spot is programmed to perform tasks such as reading gauges, inspecting for corrosion, mapping the facility, and detecting methane leaks. The deployment aims to reduce human exposure to hazardous environments and free up personnel for more complex tasks.
Source
Trimble and Boston Dynamics form construction robotics alliance
2020-10-20 - Partnership - The jointly developed solution combined Spot autonomous mobility with Trimble sensors and field software for site scans, surveying and progress monitoring. Trimble received exclusivity to sell and support Spot with integrated scanning, total-station and GNSS technologies for the construction market. Mortenson piloted Spot with Trimble SPS986 GNSS at solar farms to document site conditions, while general availability was planned for the second quarter of 2021.
Source
Boston Dynamics expands Spot robot sales to Europe and Canada
2020-09-09 - Market Signal - Boston Dynamics expanded commercial Spot sales to the European Union, United Kingdom and Canada. The expansion followed Spot’s U.S. launch and Early Adopter Program. European users including Foster + Partners, Merck KGaA and Kvaerner Stord had integrated Spot into operations.
Source
Boston Dynamics deploys Spot at insideFPL for storm data collection
2020-02-03 - Deployment - Deploys Spot in field environments for real-time storm data collection. Enables improved data coverage while minimizing risk to human operators. Signals strategic partnership with insideFPL for enhanced operational efficiency.
Source
Boston Dynamics launches Spot for purchase to enhance industrial efficiency
2020-06-16 - Product Launch - Early adopters have demonstrated Spot's ability to reduce risks in various industrial processes. The availability of Spot marks a significant step in the adoption of agile mobile robots. Boston Dynamics builds high-performance mobile robots including Spot for industrial and field inspection, Stretch for warehouse trailer unloading, and Atlas for advanced humanoid mobility.
Source
Boston Dynamics partners with BrasfieldGorrie and DroneDeploy to automate construction site documentation
2021-03-04 - Partnership - The collaboration utilizes Spot to streamline monitoring processes, reducing time and costs associated with manual documentation. This partnership aims to enhance efficiency on construction sites, allowing workers to focus on more valuable tasks.
Source

Context

Market context

Spot is Boston Dynamics' quadruped robot for industrial inspection, data collection and site monitoring across energy, construction and infrastructure environments.

Target environment: Industrial plants, construction sites, energy facilities and outdoor infrastructure.
Workflow context: Autonomous patrols, remote inspection, sensor payload deployment and site monitoring in hazardous or hard-to-reach locations.
Customer context: Infrastructure operators, energy companies, construction firms and industrial inspection teams.
Deployment model: Commercial product with broad deployment across multiple industries and geographies.
Commercial maturity: One of the most established real-world legged robots. Broad commercial deployment across inspection, construction and energy use cases.
Adoption constraints: Payload capacity and battery runtime limit continuous operation. Effective for inspection but not for heavy manipulation tasks.
Market position: The reference standard for industrial inspection quadrupeds. Serves as the benchmark against which other inspection robots are compared.
Adjacent products: ANYmal, B2, Go2

Comparable Systems

ANYmal
ANYbotics - Quadruped
A2
Unitree - Quadruped
B2
Unitree - Quadruped
X30
Deep Robotics - Quadruped
PUDU D5
Pudu Robotics - Quadruped
Unitree As2
Unitree - Quadruped

Related Systems

LYNX M20
Deep Robotics - Quadruped
LYNX M20S
Deep Robotics - Quadruped
LYNX S10
Deep Robotics - Quadruped
MagicDog-W
MagicLab - Quadruped