ANYmal

Source-backed capabilities

• Capability areas: Autonomous navigation
• Workflows: Industrial inspection
• Operating environments: Industrial facility
• Target markets: Industrial operators reducing manual inspection exposure and improving routine asset data capture.
• Deployment model: Enterprise robot deployment with inspection software, docking and operations integration.
• Multi-terrain locomotion

  Research demonstration - 2026-06-23 - Policies are evaluated in simulation on flat and rough terrains, and deployed on ANYmal hardware.

  Source
• Navigation and obstacle avoidance

  Research demonstration - 2024-09-11 - Perceptive Pedipulation with Local Obstacle Avoidance

  Source
• Dynamic locomotion

  Research demonstration - 2023-06-26 - The ANYmal Parkour paper proposes a learned hierarchy for walking, jumping, climbing, and crouching through parkour-like obstacles.

  Source
• Fall recovery

  Research demonstration - 2019-01-24 - It reports dynamic motor skills such as fast locomotion, fall recovery, and robustness to pushes, slopes, and uneven terrain.

  Source
• Whole-body loco-manipulation

  Research demonstration - 2025-09-16 - Collaborative Loco-Manipulation for Pick-and-Place Tasks with Dynamic Reward Curriculum

  Source
• Pick and place

  Research demonstration - 2025-09-16 - The authors present a hierarchical RL pipeline for training one-armed legged robots to perform pick-and-place (P&P) tasks end-to-end -- from approaching the payload to releasing it at a target area -- in both single-robot and cooperative dual-robot settings.

  Source
• Robotic inspection

  Commercial deployment - ANYbotics documents ANYmal running recurring autonomous inspection missions at Vigier Ciment, collecting plant measurements for maintenance teams over an extended customer deployment.

  Source
• Industrial maintenance support

  Commercial deployment - ANYbotics documents ANYmal running recurring autonomous inspection missions at Vigier Ciment, collecting plant measurements for maintenance teams over an extended customer deployment.

  Source
• Inspection

  Customer-site use - 2023-11-22 - Petrobras fields ANYmal X for offshore FPSO inspection

  Source
• Long-range autonomous transit

  Research demonstration - 2024-03-29 - The authors demonstrate autonomous gait transitions on ANYmal-C and Unitree Go1, including stable four-beat walking at lower speed and trotting at higher speed.

  Source

• Named Customer Site

  ANYmal D at Northern Lights CCS facility - 2025-06-23 - Equinor - industrial inspection and remote monitoring - Equinor deployed ANYmal D at the Northern Lights CCS facility in Oygarden for autonomous inspection and remote monitoring workflows.

  Source
• Customer Bound Units

  6 ANYmal X units for Petrobras offshore inspection pilot - 2023-11-22 - Petrobras - offshore FPSO inspection - Petrobras invested in six ANYmal X units and field-tested the robot on FPSO P-74 as part of a long-term offshore inspection pilot.

  Source
• Named Pilot Site

  ANYmal X tested on Aker BP Valhall platform - 2023-11-15 - Aker BP - remote offshore inspection - ANYbotics, Aker BP, and Cognite tested ANYmal X on Aker BP's Valhall platform for remote offshore inspection and digital-twin integration.

  Source
• Named Pilot Site

  ANYmal X tested at BASF Ludwigshafen - 2023-08-04 - BASF - Ex-rated industrial inspection - BASF tested ANYmal X at its Ludwigshafen site for automated visual, thermal, and acoustic inspections in Ex-rated plant areas.

  Source

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

• Leica BLK ARC

  2022-09-13 - Pilot - Mounted - Physical - ANYbotics demonstrated ANYmal carrying an integrated Leica BLK ARC scanner during the Implenia construction-site project.

  Source

Supply / Components

• ANYmal

  Intel Core I7 Processors For Anybotics Anymal - Compute & Control - Intel - ANYbotics specifies two Intel Core i7 processors in ANYmal - source: anybotics.com

  Source

• Learning Perceptive Platform Adaptive Locomotion Controllers for Quadrupedal Robots

  2026-06-23 - Research Publication - Universal quadrupedal locomotion remains limited by the difficulty of integrating perception across diverse robot morphologies. Policies are evaluated in simulation on flat and rough terrains, and deployed on ANYmal hardware.

  Source
• Learning Perceptive Platform Adaptive Locomotion Controllers for Quadrupedal Robots

  2026-06-23 - Research Publication - Universal quadrupedal locomotion remains limited by the difficulty of integrating perception across diverse robot morphologies. Policies are evaluated in simulation on flat and rough terrains, and deployed on ANYmal hardware.

  Source
• ZackOo23/Software-Development-for-Advanced-RL-techniques

  2026-06-01 - Research Publication - This repository extends an ANYmal-D PPO baseline into a more maintainable robotics learning pipeline for advanced simulation. ANYmal-D Learning Pipeline Reproducible ANYmal-D robotics learning pipeline with PPO baseline training, structured experiment logging, waypoint-based demonstration collection, and preparation for imitation learning with Diffusion Policy or Flow Matching. Use the generated demonstration dataset for imitation learning.

  Source
• SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion

  2026-04-10 - Research Publication - The authors introduce SafeMind, a differentiable stochastic safety-control framework that unifies probabilistic Control Barrier Functions with semantic context understanding and meta-adaptive risk calibration. SafeMind is deployed on Unitree A1 and ANYmal C at 200 Hz and validated across 12 terrain types, dynamic obstacles, morphology perturbations, and semantically defined tasks.

  Source
• GrandTour dataset paper releases large-scale ANYmal-D legged-robot perception data

  2026-02-20 - Research Publication - The GrandTour paper introduces a large open-access legged-robotics dataset for state estimation, SLAM, perception, and multi-modal learning. The dataset was collected with an ANYbotics ANYmal-D quadruped carrying the Boxi multi-modal sensor payload across indoor and outdoor environments. The dataset gives ANYmal-D a large-scale public benchmark for legged-robot perception, state estimation, SLAM, and multi-modal learning.

  Source
• Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learning

  2026-01-24 - Research Publication - The authors propose a Learning Progress-based Automatic Curriculum Reinforcement Learning (LP-ACRL) framework, which estimates the agent's learning progress online and adaptively adjusts the task-sampling distribution, thereby enabling automatic curriculum generation without prior knowledge of the difficulty distribution over the task space. Policies trained with LP-ACRL enable the ANYmal D quadruped to achieve and maintain stable, high-speed locomotion at 2.5 m/s linear velocity and 3.0 rad/s angular velocity across diverse terrains, including stairs, slopes, gravel, and low-friction flat surfaces--whereas previous methods have generally been limited to high speeds on flat terrain or low speeds on complex terrain.

  Source
• Large-Scale Autonomous Gas Monitoring for Volcanic Environments: A Legged Robot on Mount Etna

  2026-01-12 - Research Publication - The authors present a legged robotic system for autonomous volcanic gas analysis, utilizing the quadruped ANYmal, equipped with a quadrupole mass spectrometer system. The authors evaluated the system on Mount Etna across three autonomous missions in varied terrain, achieving successful gas-source detections with autonomy rates of 93-100%.

  Source
• Botany Meets Robotics in Alpine Scree Monitoring

  2025-11-16 - Research Publication - The paper presents a novel approach for scree habitat monitoring using a legged robot to assist botanists in data collection and species identification. This paper presents a novel approach for scree habitat monitoring using a legged robot to assist botanists in data collection and species identification.

  Source
• PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion

  2025-10-21 - Research Publication - The authors propose Phase-Guided Terrain Traversal (PGTT), a perception-aware deep-RL approach that overcomes these limitations by enforcing gait structure purely through reward shaping, thereby reducing inductive bias in policy learning compared to oscillator/IK-conditioned action priors. The authors validate PGTT on a Unitree Go2 using a real-time LiDAR elevation-to-heightmap pipeline, and the authors report preliminary results on ANYmal-C obtained with the same hyperparameters.

  Source
• Bridging Research and Practice in Simulation-based Testing of Industrial Robot Navigation Systems

  2025-10-10 - Research Publication - The paper presents the industrial adoption of Surrealist, a simulation-based test generation framework originally for UAVs, now applied to the ANYmal quadrupedal robot for industrial inspection. In a pilot phase, generated test suites revealed critical weaknesses in one experimental algorithm (40.3% success rate) and served as an effective benchmark to prove the superior robustness of another (71.2% success rate).

  Source
• Bridging Research and Practice in Simulation-based Testing of Industrial Robot Navigation Systems

  2025-10-10 - Research Publication - The paper presents the industrial adoption of Surrealist, a simulation-based test generation framework originally for UAVs, now applied to the ANYmal quadrupedal robot for industrial inspection. In a pilot phase, generated test suites revealed critical weaknesses in one experimental algorithm (40.3% success rate) and served as an effective benchmark to prove the superior robustness of another (71.2% success rate).

  Source
• Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies

  2025-10-08 - Research Publication - This work focuses on sampling strategies of configuration variations for generating robust universal locomotion policies for quadrupedal robots. All training was conducted using the RaiSim simulation environment, tested in simulation on a range of diverse quadrupeds, and zero-shot deployed onto hardware using the ANYmal quadruped robot.

  Source
• Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies

  2025-10-08 - Research Publication - This work focuses on sampling strategies of configuration variations for generating robust universal locomotion policies for quadrupedal robots. All training was conducted using the RaiSim simulation environment, tested in simulation on a range of diverse quadrupeds, and zero-shot deployed onto hardware using the ANYmal quadruped robot.

  Source
• Collaborative Loco-Manipulation for Pick-and-Place Tasks with Dynamic Reward Curriculum

  2025-09-16 - Research Publication - The authors present a hierarchical RL pipeline for training one-armed legged robots to perform pick-and-place (P&P) tasks end-to-end -- from approaching the payload to releasing it at a target area -- in both single-robot and cooperative dual-robot settings. The authors validate the method through real-world experiments using ANYmal D platforms in both single- and dual-robot scenarios.

  Source
• Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots

  2025-09-08 - Research Publication - The authors propose a framework that integrates sim-to-real reinforcement learning with a physics-grounded energy model for permanent magnet synchronous motors. All code, models, and datasets will be released.

  Source
• Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots

  2025-09-08 - Research Publication - The authors propose a framework that integrates sim-to-real reinforcement learning with a physics-grounded energy model for permanent magnet synchronous motors. All code, models, and datasets will be released.

  Source
• Constrained Style Learning from Imperfect Demonstrations under Task Optimality

  2025-07-12 - Research Publication - The authors introduce an adaptively adjustable Lagrangian multiplier to guide the agent to imitate demonstrations selectively, capturing stylistic nuances without compromising task performance. The authors validate the approach across multiple robotic platforms and tasks, demonstrating both robust task performance and high-fidelity style learning.

  Source
• Building Forest Inventories with Autonomous Legged Robots -- System, Lessons, and Challenges Ahead

  2025-06-25 - Research Publication - The paper presents a prototype system for autonomous, under-canopy forest inventory with legged platforms. The authors report the performance of the system from trials executed over one and a half years in forests in three European countries.

  Source
• Learning Physical Systems: Symplectification via Gauge Fixing in Dirac Structures

  2025-06-23 - Research Publication - The authors tackle this foundational limitation by introducing Presymplectification Networks (PSNs), the first framework to learn the symplectification lift via Dirac structures, restoring a non-degenerate symplectic geometry by embedding constrained systems into a higher-dimensional manifold. The authors demonstrate the method on the dynamics of the ANYmal quadruped robot, a challenging contact-rich, multibody system.

  Source
• Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning

  2025-05-16 - Research Publication - Legged robots are well-suited for navigating terrains inaccessible to wheeled robots, making them ideal for applications in search and rescue or space exploration. However, current control methods often struggle to generalize across diverse, unstructured environments. The work is explicitly tied to ANYmal, making the product binding high confidence. The artifact adds external research coverage for ANYmal beyond company-authored releases.

  Source
• Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning

  2025-05-15 - Research Publication - While foundation models offer promise toward improving robot safety in out-of-distribution (OOD) scenarios, how to effectively harness their generalist knowledge for real-time, dynamically feasible response remains a crucial problem. We present FORTRESS, a joint reasoning and planning framework that generates semantically safe fallback strategies to prevent safety-critical, OOD failures. The work is explicitly tied to ANYmal, making the product binding high confidence. The artifact adds external research coverage for ANYmal beyond company-authored releases.

  Source
• FOCI: Trajectory Optimization on Gaussian Splats

  2025-05-13 - Research Publication - 3D Gaussian Splatting (3DGS) has recently gained popularity as a faster alternative to Neural Radiance Fields (NeRFs) in 3D reconstruction and view synthesis methods. Leveraging the spatial information encoded in 3DGS, this work proposes FOCI (Field Overlap Collision Integral), an algorithm that is able to optimize trajectories directly on the Gaussians themselves. The work is explicitly tied to ANYmal, making the product binding high confidence. The artifact adds external research coverage for ANYmal beyond company-authored releases.

  Source
• Offline Adaptation of Quadruped Locomotion using Diffusion Models

  2024-11-13 - Research Publication - The authors present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training. The authors verify the validity of their approach with hardware experiments on the ANYmal quadruped platform.

  Source
• SDS -- See it, Do it, Sorted: Quadruped Skill Synthesis from Single Video Demonstration

  2024-10-15 - Research Publication - ANYmal) and outperforms prior work in data efficiency, training time and engineering effort. Further materials and the code are open-source under: https://rpl-cs-ucl.github.io/SDSweb/.

  Source
• Constrained skill discovery paper deploys unsupervised locomotion on ANYmal

  2024-10-10 - Research Publication - The paper proposes constrained unsupervised skill discovery for quadruped locomotion using a latent representation over states. The authors report deployment of learned policies on a real ANYmal quadruped robot for zero-shot Cartesian-state reaching.

  Source
• Obstacle-Avoidant Leader Following with a Quadruped Robot

  2024-10-01 - Research Publication - This work presents a virtual leash with which a robot can naturally follow an operator. The authors successfully validate on the ANYmal platform the robustness and performance of their entire pipeline in real-world experiments.

  Source
• Whole-body End-Effector Pose Tracking

  2024-09-24 - Research Publication - The study addresses these limitations by introducing a whole-body RL formulation for end-effector pose tracking in a large workspace on rough, unstructured terrains. The authors validate their approach on the ANYmal quadrupedal robot with a six DoF robotic arm. On deployment, it achieves a pose-tracking error of 2.64 cm and 3.64 degrees, outperforming existing competitive baselines.

  Source
• InteLiPlan: An Interactive Lightweight LLM-Based Planner for Domestic Robot Autonomy

  2024-09-22 - Research Publication - The authors introduce an interactive LLM-based framework designed to enhance the autonomy and robustness of domestic robots, targeting embodied intelligence. The authors evaluate their method in both simulation and on the real robot platforms, including a Toyota Human Support Robot and an ANYmal D robot with a Unitree Z1 arm. InteLiPlan achieves comparable performance to state-of-the-art LLM-based robotics planners, while using only real-time onboard computing.

  Source
• Perceptive Pedipulation with Local Obstacle Avoidance

  2024-09-11 - Research Publication - To address this limitation, the authors introduce a reinforcement learning-based approach to train a whole-body obstacle-aware policy that tracks foot position commands while simultaneously avoiding obstacles. The authors analyze the performance of their method through a set of simulation experiments and successfully deploy the learned policy on the ANYmal quadruped, demonstrating its capability to follow foot commands while navigating around static and dynamic obstacles. Videos of the experiments are available at sites.google.com/leggedrobotics.com/perceptive-pedipulation.

  Source
• Learning to Open and Traverse Doors with a Legged Manipulator

  2024-09-07 - Research Publication - To address this, the authors propose a learning-based controller for a legged manipulator to open and traverse through doors. The policy was deployed on the ANYmal legged robot with an arm and achieved a success rate of 95.0% in repeated trials conducted in an experimental setting. A video overview of the method and experiments can be found at youtu.be/tQDZXN_k5NU.

  Source
• Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigation

  2024-08-29 - Research Publication - The study proposes a cross-modal self-supervised learning framework for vision-based environmental physical parameter estimation, which paves the way for future physical-property-aware locomotion and navigation. The authors validate their physical decoder in simulation and the real world using a quadruped ANYmal robot, outperforming an existing baseline method. The authors show that their visual network can predict the physical properties in indoor and outdoor experiments while allowing fast adaptation to new environments.

  Source
• IN-Sight: Interactive Navigation through Sight

  2024-08-01 - Research Publication - In response, the authors introduce IN-Sight, a novel approach to self-supervised path planning, enabling more effective navigation strategies through interaction with obstacles. Moreover, the authors demonstrate the system's real-world applicability with zero-shot sim-to-real transfer, deploying their planner on the legged robot platform ANYmal, showcasing its practical potential for interactive navigation in real environments.

  Source
• Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotion

  2024-05-29 - Research Publication - Alternatively, the authors present Gaitor, which learns a disentangled and 2D representation across locomotion gaits. The authors evaluate Gaitor in both simulation and the real world on the ANYmal C platform. An overview of the methods and results in this paper is found at https://youtu.be/eVFQbRyilCA.

  Source
• Autonomous Forest Inventory with Legged Robots: System Design and Field Deployment

  2024-04-22 - Research Publication - The authors present a solution for autonomous forest inventory with a legged robotic platform. Their UK experiment at the Forest of Dean with the ANYmal D legged platform, achieved an autonomous survey of a 0.96 hectare plot in 20 min, identifying over 100 trees with typical DBH accuracy of 2 cm.

  Source
• Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation

  2024-04-04 - Research Publication - This work leverages a Population-Based Reinforcement Learning (PBRL) approach and a GPU-accelerated physics simulator to enhance the exploration capabilities of RL by concurrently training multiple policies in parallel. The experiments are performed on four challenging tasks in Isaac Gym -- Anymal Terrain, Shadow Hand, Humanoid, Franka Nut Pick -- by analyzing the effect of population size and mutation mechanisms for hyperparameters. Code and videos of the learned policies are available on their project website (https://sites.google.com/view/pbrl).

  Source
• Adaptive energy-regularization paper trains efficient gait transitions on ANYmal-C

  2024-03-29 - Research Publication - The paper proposes an adaptive energy reward for reinforcement-learning locomotion so quadrupeds can choose efficient gaits across different speeds. The authors demonstrate autonomous gait transitions on ANYmal-C and Unitree Go1, including stable four-beat walking at lower speed and trotting at higher speed. It adds meaningful ANYmal research context around energy efficiency and gait selection, not only terrain robustness.

  Source
• Neuromorphic quadratic programming for efficient and scalable model predictive control

  2024-01-26 - Research Publication - Here, the authors present a method to solve convex continuous optimization problems with quadratic cost functions and linear constraints on Intel's scalable neuromorphic research chip Loihi 2. When applied to model predictive control (MPC) problems for the quadruped robotic platform ANYmal, this method achieves over two orders of magnitude reduction in combined energy-delay product compared to the state-of-the-art solver, OSQP, on (edge) CPUs and GPUs with solution times under ten milliseconds for various problem sizes. These results demonstrate the benefit of non-von-Neumann architectures for robotic control applications.

  Source
• Learning Agile Locomotion on Risky Terrains

  2023-11-17 - Research Publication - Given that the robot needs to rapidly adapt its velocity on these terrains, the authors formulate the task as a navigation task instead of the commonly used velocity tracking which constrains the robot's behavior and propose an exploration strategy to overcome sparse rewards and achieve high robustness. The authors validate their proposed method through simulation and real-world experiments on an ANYmal-D robot achieving peak forward velocity of >= 2.5 m/s on sparse stepping stones and narrow balance beams.

  Source
• Momentum-Aware Trajectory Optimisation using Full-Centroidal Dynamics and Implicit Inverse Kinematics

  2023-10-09 - Research Publication - Their proposed formulation exploits the system's high-order nonlinearities, such as the nonholonomy of the angular momentum, in order to produce feasible, high-acceleration manoeuvres. By leveraging the full-centroidal dynamics of the quadruped ANYmal C and directly optimising its footholds and contact forces, the framework is capable of producing efficient motion plans with low computational overhead. Finally, the authors deploy their proposed framework on the ANYmal C platform, and demonstrate its true capabilities through real-world experiments, with the successful execution of high-acceleration motions, such as linear and rotational jumps.

  Source
• Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End

  2023-10-05 - Research Publication - The authors validate their approach in simulation and on the real quadruped robot ANYmal running in real-time (<10 ms CPU inference). In a quantitative comparison with existing heuristic-based locally reactive planners, their policy increases the success rate over 30% when facing perception failures.

  Source
• Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning

  2023-09-25 - Research Publication - The study proposes a risk sensitive locomotion training method employing distributional reinforcement learning to consider safety explicitly. The authors show emergent risk sensitive locomotion behavior in simulation and on the quadrupedal robot ANYmal. Videos of the experiments and code are available at https://sites.google.com/leggedrobotics.com/risk-aware-locomotion.

  Source
• ANYmal Parkour paper trains agile navigation for quadrupedal robots

  2023-06-26 - Research Publication - The ANYmal Parkour paper proposes a learned hierarchy for walking, jumping, climbing, and crouching through parkour-like obstacles. The authors report successful real-world transfer on hardware at speeds up to two meters per second. The work gives ANYmal a concrete benchmark for agile locomotion and real-world policy transfer.

  Source
• Perceptive locomotion paper validates real-time NMPC climbing on ANYmal

  2022-08-17 - Research Publication - The paper presents a full perception, planning, and control pipeline for optimizing all robot degrees of freedom in real time. Experiments on ANYmal cover gaps, slopes, and stepping stones, including dynamic climbing behaviors. It expands ANYmal research coverage from blind locomotion into perception-aware nonlinear model predictive control.

  Source
• ANYmal challenging-terrain paper demonstrates blind locomotion in natural environments

  2020-10-21 - Research Publication - The Science Robotics paper trains a learning-based controller for quadrupedal locomotion over difficult natural terrain. The controller is deployed on two generations of ANYmal robots in outdoor settings beyond the reach of prior published legged-locomotion work. The result is one of the clearest research anchors for ANYmal as a rugged field-locomotion platform.

  Source
• Science Robotics paper learns agile motor skills on ANYmal

  2019-01-24 - Research Publication - The paper trains a neural-network locomotion controller in simulation and deploys it on the ANYmal quadruped. It reports dynamic motor skills such as fast locomotion, fall recovery, and robustness to pushes, slopes, and uneven terrain. This is a landmark ANYmal result because it helped establish sim-to-real reinforcement learning as a practical route for legged-robot control.

  Source

Media library

• ANYmal industrial inspection

  image · ANYbotics

  Source
• ANYmal stair-climbing inspection

  image · ANYbotics

  Source
• ANYmal inspection at RTE

  image · ANYbotics

  Source
• World's first autonomous offshore robot: ANYmal

  video · ANYbotics

  Source

Official specifications, onboarding and technical references, exact-platform imagery and a verified field video for the ANYbotics ANYmal robot.

• ANYmal product reference

  WEB · ANYmal · ANYbotics

  Source
• ANYmal specifications

  PDF · ANYmal · ANYbotics

  Source
• ANYmal API white paper

  WEB · ANYmal API · ANYbotics

  Source
• ANYmal customer onboarding

  WEB · ANYmal deployment · ANYbotics

  Source
• ANYbotics white papers and ebooks

  WEB · ANYmal technical resources · ANYbotics

  Source

• ANYbotics pilots autonomous access through controlled doors at GE Vernova power plant

  2026-09-17 - Deployment - ANYmal operated for several weeks at Whitegate, repeatedly requesting access, passing controlled doors and continuing inspection routes without manual intervention. LEGIC supplies secure digital credentials, while dormakaba provides access management and automated door solutions integrated with the plant's existing processes. The partners are working toward commercial availability and are exploring elevators, gates and turnstiles as additional access points.

  Source
• Learning Perceptive Platform Adaptive Locomotion Controllers for Quadrupedal Robots

  2026-06-23 - Research Publication - Universal quadrupedal locomotion remains limited by the difficulty of integrating perception across diverse robot morphologies. Policies are evaluated in simulation on flat and rough terrains, and deployed on ANYmal hardware.

  Source
• ANYbotics passes 200 ANYmal robots in productive use

  2026-03-30 - Market Signal - More than 200 ANYmal robots were in productive use worldwide. SAP Field Service Management integration enabled work-order dispatch to ANYmal and inspection results back into SAP. The integration linked industrial inspection robots with enterprise maintenance and asset-management workflows.

  Source
• Yokogawa and ANYbotics sign partnership to integrate OpreX Robot Management Core with ANYmal inspection robots

  2026-02-10 - Partnership - Yokogawa and ANYbotics signed a partnership agreement to integrate Yokogawa's OpreX Robot Management Core software with the software stack of ANYbotics' ANYmal robots. The integration covers both explosion-proof and non-explosion-proof inspection robots and is aimed at industrial operators in oil and gas, power, and metals. The partnership expands ANYbotics' position in industrial inspection through a software and deployment ecosystem relationship with Yokogawa.

  Source
• Bridging Research and Practice in Simulation-based Testing of Industrial Robot Navigation Systems

  2025-10-10 - Research Publication - The paper presents the industrial adoption of Surrealist, a simulation-based test generation framework originally for UAVs, now applied to the ANYmal quadrupedal robot for industrial inspection. In a pilot phase, generated test suites revealed critical weaknesses in one experimental algorithm (40.3% success rate) and served as an effective benchmark to prove the superior robustness of another (71.2% success rate).

  Source
• Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies

  2025-10-08 - Research Publication - This work focuses on sampling strategies of configuration variations for generating robust universal locomotion policies for quadrupedal robots. All training was conducted using the RaiSim simulation environment, tested in simulation on a range of diverse quadrupeds, and zero-shot deployed onto hardware using the ANYmal quadruped robot.

  Source
• Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots

  2025-09-08 - Research Publication - The authors propose a framework that integrates sim-to-real reinforcement learning with a physics-grounded energy model for permanent magnet synchronous motors. All code, models, and datasets will be released.

  Source
• Equinor deploys ANYmal at Northern Lights CCS facility

  2025-06-23 - Deployment - The robot was autonomously running through the facility within the first week of deployment. Use cases include CO2 monitoring, perimeter surveys and frequent inspections at the normally unmanned site. The deployment places Equinor's technology into inspection, monitoring or infrastructure automation workflows beyond a lab-only setting.

  Source
• ANYbotics launches gas leak and gas presence detection capability for ANYmal

  2025-06-18 - Product Launch - ANYbotics launched gas leak and gas presence detection capability for its ANYmal inspection robot. The release adds autonomous gas-sensing workflows to the company's industrial inspection stack. The launch extends ANYmal's role from visual and thermal inspection into hazardous-environment gas monitoring.

  Source
• ANYbotics launches ANYmal Research Manipulation Payload

  2025-05-21 - Product Launch - The payload adds mobile-manipulation hardware to the ANYmal Research platform. ANYbotics developed the system with Duatic. The named development collaboration was completed for the launch.

  Source
• Kanadevia Inova selects ANYbotics as preferred ground-robot supplier

  2025-02-25 - Partnership - The preferred-supplier agreement covers operations, maintenance and digital-service offerings. A successful Slough demonstration preceded the broader agreement.

  Source
• Chironix becomes ANYbotics reseller in Australia and New Zealand

  2025-02-17 - Partnership - Chironix will offer ANYmal by direct sale and Robotics-as-a-Service. The territory covers Australia and New Zealand. The agreement includes local support, training and integration services.

  Source
• ANYbotics raises additional $60M to expand in the U.S.

  2024-12-12 - Funding - Qualcomm Ventures and Supernova Invest led the additional $60 million financing. TDK Ventures joined as a new investor alongside existing backers including Walden Catalyst, NGP Capital, Bessemer Venture Partners, Swisscanto Private Equity and Swisscom Ventures. The round took ANYbotics' company-reported cumulative funding above $130 million and supported U.S. expansion and product development.

  Source
• Equans selects ANYbotics for offshore inspection services

  2024-11-14 - Partnership - Equans selected ANYbotics as preferred ground-robot supplier. Equans plans to offer ANYmal by direct purchase or Robotics-as-a-Service. The scope is offshore substations and platforms; site-level deployments are not individually asserted.

  Source
• Gresco adds ANYmal inspection robots to U.S. utility offering

  2024-11-08 - Partnership - Gresco offers ANYmal through direct purchase and subscription models. The scope is U.S. power and utility inspection. Gresco provides local support, training and technical services.

  Source
• ANYbotics and AWS partner on ANYmal industrial inspection workflows

  2024-08-27 - Partnership - ANYbotics and AWS cooperated to make ANYmal available as an AWS Partner Solution for industrial inspection workflows, connecting robot inspection data into cloud-based industrial systems. ANYmal became available as an AWS Partner Solution. The solution targets industrial inspection data workflows.

  Source
• ANYbotics and Energy Robotics partner on inspection-data integration

  2024-06-12 - Partnership - Partnership links ANYmal inspection robots with Energy Robotics software. The collaboration was announced around ACHEMA 2024. Integration targets asset-monitoring and inspection-data workflows for industrial sites.

  Source
• ANYmal robot demonstrates autonomous inspection capabilities

  2023-12-21 - Demonstration - ANYbotics showcased the ANYmal robot's autonomous inspection and locomotion capabilities at AWS re:Invent in Las Vegas. The demonstration included the robot reading visual, thermal, and acoustic signals while avoiding obstacles. The event highlighted ANYmal's ability to perform autonomous missions in complex environments.

  Source
• Petrobras fields ANYmal X for offshore FPSO inspection

  2023-11-22 - Deployment - The program targets repetitive and hazardous inspection tasks on FPSO vessels. ANYbotics said ANYmal X was conducting autonomous inspection missions on a Petrobras FPSO. The deployment places Petrobras fields ANYmal X for offshore FPSO inspection's technology into maritime autonomy, underwater robotics or marine inspection workflows beyond a lab-only setting.

  Source
• Aker BP tests ANYmal X inspections on Valhall platform

  2023-11-15 - Deployment - The Valhall test covered two decks and 70 inspection points. ANYmal X data was integrated with Cognite Data Fusion for mission planning and inspection analysis. The deployment supported Aker BP’s plan for remote inspection on unmanned offshore platforms.

  Source
• ANYbotics deploys ANYmal X for BASF Ex-zone inspections

  2023-08-04 - Deployment - ANYmal X conducted inspection missions across multi-level Ex-zones at BASF Ludwigshafen. The deployment covered visual readings, thermal checks, pump monitoring and anomaly data collection. The deployment places ANYbotics's technology into inspection, monitoring or infrastructure automation workflows beyond a lab-only setting.

  Source
• ANYbotics raises $50 million Series B

  2023-05-16 - Funding - Walden Catalyst and NGP Capital led the $50 million Series B, with Bessemer Venture Partners also participating. Aramco Ventures, Swisscom Ventures, Swisscanto Private Equity, EquityPitcher Ventures and Verve Ventures joined the financing. The capital was allocated to international deployments and new capabilities for the ANYmal inspection platform.

  Source
• PETRONAS and ANYbotics partner to commercialize ANYmal X

  2022-03-23 - Partnership - PETRONAS and ANYbotics agreed to commercialize ANYmal X. The collaboration targets autonomous inspection in oil, gas and energy environments. ANYmal X is designed for Ex-rated industrial environments.

  Source

Market context

ANYmal is ANYbotics industrial quadruped for autonomous inspection rounds in complex facilities.

• Target environment: Oil and gas, chemicals, power, utilities, mining, metals and transport facilities.
• Workflow context: Autonomous rounds, visual inspection, thermal/acoustic sensing, anomaly detection and remote facility monitoring.
• Customer context: Industrial operators reducing manual inspection exposure and improving routine asset data capture.
• Deployment model: Enterprise robot deployment with inspection software, docking and operations integration.
• Commercial maturity: Commercially deployed industrial inspection robot.
• Adoption constraints: Requires site mapping, safety approval, inspection workflow integration and fit with facility connectivity.
• Market position: Commercial quadruped inspection platform for heavy industry and hazardous operating environments.
• Adjacent products: Spot, B2

Tags

• Peer Group: Industrial inspection quadruped, Legged quadruped mobile robot
• Workflow: Industrial inspection
• Capability: Autonomous navigation
• Deployment Environment: Industrial facility
• Stack Layer: Finished robot platform
• Commercial Stage: Benchmark reference product, Deployed platform

Comparable Systems

• Spot

  Boston Dynamics - 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