Gen3
About
About Gen3
Gen3 is available in six- and seven-axis configurations built from lightweight modular joints with integrated torque sensing and low-level control. The standard arm carries two kilograms continuously across its full workspace and up to four kilograms within its mid-range operating envelope, while the seven-axis format adds redundancy for obstacle avoidance and human-like positioning.
Kinova’s Kortex API exposes high-level commands, joint feedback and real-time control through C++, Python, ROS and ROS 2 interfaces. Developers can integrate cameras, grippers and custom end effectors or access lower-level actuator functions for control and AI research. The arm is used across manipulation, assistive robotics, medical development, education and industrial prototyping.
Capabilities
Source-backed capabilities
- Capability areas: Collaborative operation
- Workflows: Robot manipulation research
- Target markets: Robot developer platform
- Object manipulation
Claimed - Kinova presents Gen3 as a robotics research platform for vision-based manipulation, AI development and API-driven arm control.
Source - Remote and shared control
Research demonstration - 2026-07-01 - Collected real-world bimanual furniture-assembly demonstrations through VR teleoperation on Kinova Gen3 hardware. - environment: real-scale furniture-assembly research setup
Source
Supply
Supply / Components
- Gen3
Sensone T15 Force Torque Sensor For Kinova Gen3 - force_torque_sensing - Bota Systems - Bota Systems supplies sensone t15 force torque sensor for kinova gen3 for Kinova Gen3 - source: botasys.com
Source
Research
- NeuroCommitSSM: Decision-Centric Shared Autonomy for Safe Assistive Manipulation via EEG-EMG-ET Commit Readiness
2026-07-16 - Research Publication - The authors present NeuroCommitSSM, a decision-centric framework that models when to execute, not just what to do, for safe commit-to-execute control in assistive robotic manipulation.
Source - Safe Execution of RL Policies via Acceleration-based CBF-QP Constraint Enforcement for Real-World Robotic Deployments
2026-07-16 - Research Publication - A physical H1 deployment reports 92% fewer constraint violations under the safety layer.
Source - One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic Maps
2026-07-10 - Research Publication - The authors propose a novel one-shot multimodal LfD framework for the segmentation, encoding, and reproduction of force-inclusive demonstrations.
Source - FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model
2026-07-01 - Research Publication - Current work on robot furniture assembly mostly focuses on toy-scale settings or single-arm manipulation. We introduce FurnitureVLA, the first systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models (VLAs). We formalize the task, develop a scalable simulation pipeline for expert data generation and evaluation, and build a VR teleoperation system for single-operator bimanual cont
Source - JOIN: Anchor-Grasp-Conditioned Joining via Opposition, Inference, and Navigation for Bimanual Assistive Manipulation
2026-06-09 - Research Publication - Assistive mobility and manipulation platforms have received increasing attention as a means of restoring independence to individuals with disabilities.
Source - muslim-adedamola/finetune-octo-kinova-hybrid
2026-04-24 - Research Publication - Finetuning and deploying Octo, a VLA on a Kinova Gen3 (7-DoF) robot for goal-image-conditioned bottle pick-and-lift using diffusion arm actions, a BCE gripper head, and latency-aware receding-horizon control.
Source - Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems
2026-04-21 - Research Publication - This paper presents a model-based reinforcement learning (RL) framework for optimal closed-loop control of nonlinear robotic systems. The proposed approach learns linear lifted dynamics through Koopman operator theory and integrates the resulting model into an actor-critic architecture for policy optimization, where the policy represents a parameterized closed-loop controller. To reduce computational cost and mitigat
Source - Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation
2026-04-04 - Research Publication - Enabling robots to learn long-horizon manipulation tasks from a handful of demonstrations remains a central challenge in robotics. Existing neuro-symbolic approaches often rely on hand-crafted symbolic abstractions, semantically labeled trajectories or large demonstration datasets, limiting their scalability and real-world applicability. We present a scalable neuro-symbolic framework that autonomously constructs symb
Source - Whole-Body Safe Control of Robotic Systems with Koopman Neural Dynamics
2026-03-04 - Research Publication - Controlling robots with strongly nonlinear, high-dimensional dynamics remains challenging, as direct nonlinear optimization with safety constraints is often intractable in real time. The Koopman operator offers a way to represent nonlinear systems linearly in a lifted space, enabling the use of efficient linear control. We propose a data-driven framework that learns a Koopman embedding and operator from data, and int
Source - RL-Based Coverage Path Planning for Deformable Objects on 3D Surfaces
2026-03-03 - Research Publication - Currently, manipulation tasks for deformable objects often focus on activities like folding clothes, handling ropes, and manipulating bags. However, research on contact-rich tasks involving deformable objects remains relatively underdeveloped. When humans use cloth or sponges to wipe surfaces, they rely on both vision and tactile feedback. Yet, current algorithms still face challenges with issues like occlusion, whil
Source - RoboSubtaskNet: Temporal Sub-task Segmentation for Human-to-Robot Skill Transfer in Real-World Environments
2026-02-10 - Research Publication - Temporally locating and classifying fine-grained sub-task segments in long, untrimmed videos is crucial to safe human-robot collaboration. Unlike generic activity recognition, collaborative manipulation requires sub-task labels that are directly robot-executable. We present RoboSubtaskNet, a multi-stage human-to-robot sub-task segmentation framework that couples attention-enhanced I3D features (RGB plus optical flow)
Source - Neural Minimum-Distance Estimation for Collision-Aware Operation of Multi-Arm Laparoscopy Surgical Robots Through Learning-from-Simulation
2026-01-21 - Research Publication - This study presents an integrated framework for enhancing the safety and operational efficiency of robotic arms in laparoscopic surgery by addressing minimum distance estimation between multi-arm manipulators and the associated collision-aware warning.
Source - The Role of Consequential and Functional Sound in Human-Robot Interaction: Toward Audio Augmented Reality Interfaces
2025-11-20 - Research Publication - Developing a deeper understanding of how robot sounds influence human experience, and how technologies such as augmented reality (AR) modulate these effects, can enable the design of more socially acceptable robots and more effective, intuitive human-robot interfaces.
Source - XFlowMP: Task-Conditioned Motion Fields for Generative Robot Planning with Schrodinger Bridges
2025-11-02 - Research Publication - The study presents XFlowMP, a task-conditioned generative motion planner that models robot trajectory evolution as entropic flows bridging stochastic noises and expert demonstrations via Schrodinger bridges given the inquiry task configuration.
Source - Reliable Robotic Task Execution in the Face of Anomalies
2025-10-27 - Research Publication - The study presents a framework that couples a learned policy with a method to detect visual anomalies during policy deployment and to perform recovery behaviours when necessary, thereby aiming to prevent failures.
Source - A Cross-Environment and Cross-Embodiment Path Planning Framework via a Conditional Diffusion Model
2025-10-21 - Research Publication - The primary goal of this research is to develop a path planning framework capable of generalizing to unseen environments and new robotic manipulators without the need for retraining.
Source - A Bimanual Gesture Interface for ROS-Based Mobile Manipulators Using TinyML and Sensor Fusion
2025-09-23 - Research Publication - This paper presents a dual-hand gesture interface that integrates TinyML, spectral analysis, and sensor fusion within a ROS framework to address these limitations.
Source - CRISP -- Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation
2025-09-08 - Research Publication - The authors present CRISP, a lightweight C++ implementation of compliant Cartesian and joint-space controllers for the ROS2 control standard, designed for seamless integration with high-level learning-based policies as well as teleoperation.
Source - Collision-Free Trajectory Planning and control of Robotic Manipulator using Energy-Based Artificial Potential Field (E-APF)
2025-08-10 - Research Publication - To address this limitation, an Energy-based Artificial Potential Field (APF) framework is proposed in this paper that integrates position and velocity-dependent potential functions.
Source - RAKOMO: Reachability-Aware K-Order Markov Path Optimization for Quadrupedal Loco-Manipulation
2025-07-25 - Research Publication - However, trajectory optimization methods often face challenges due to the hybrid dynamics introduced by contact discontinuities, and tend to neglect leg limitations during planning for computational reasons.
Source - Task and Joint Space Dual-Arm Compliant Control
2025-04-29 - Research Publication - To address this, the authors present a real-time, open-source impedance controller that smoothly interpolates between joint-space and task-space compliance.
Source - Data-Enabled Neighboring Extremal: Case Study on Model-Free Trajectory Tracking for Robotic Arm
2025-04-09 - Research Publication - To overcome this limitation, the authors propose the data-enabled neighboring extremal (DeeNE) framework, which significantly reduces computational cost while preserving control performance.
Source - Demonstrating a Control Framework for Physical Human-Robot Interaction Toward Industrial Applications
2025-02-05 - Research Publication - This paper introduces a versatile control framework designed to bridge this gap by incorporating the torque-based control modes: compliance control, null-space compliance, and dual compliance, all in static and dynamic scenarios.
Source - Toward Zero-Shot User Intent Recognition in Shared Autonomy
2025-01-14 - Research Publication - The authors propose and study a zero-shot, vision-only shared autonomy (VOSA) framework designed to allow robots to use end-effector vision to estimate zero-shot human intents in conjunction with blended control to help humans accomplish manipulation tasks with unknown and dynamically changing object locations.
Source - Robustifying Long-term Human-Robot Collaboration through a Multimodal and Hierarchical Framework
2024-11-24 - Research Publication - To address these challenges, the authors model the long-term HRC task through a hierarchical task graph and presents a novel multimodal and hierarchical framework to enable robots to better assist humans to advance on the task graph.
Source - AmirhosseinSoltan/Robot-Learning
2024-10-27 - Research Publication - Learning-based Dynamic Motion Primitives of a Kinova Gen3 robotic arm using behavior cloning and PPO in Gazebo simulation with ROS and Gymnasium.
Source - A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation
2024-04-08 - Research Publication - To investigate the utility of brain-inspired sensing and data processing, the authors developed a neuromorphic approach to obstacle avoidance on a camera-equipped manipulator.
Source - The Grasp Reset Mechanism: An Automated Apparatus for Conducting Grasping Trials
2024-02-28 - Research Publication - Towards the goal of more advanced grasping, the authors present the Grasp Reset Mechanism (GRM), a fully automated apparatus for conducting large-scale grasping trials.
Source - Learning Lyapunov-Stable Polynomial Dynamical Systems through Imitation
2023-10-31 - Research Publication - To mitigate this problem, the authors present an approach for learning a globally stable nonlinear dynamical system as a motion planning policy.
Source - Mobile Manipulation Platform for Autonomous Indoor Inspections in Low-Clearance Areas
2023-09-19 - Research Publication - Mobile manipulators have been used for inspection, maintenance and repair tasks over the years, but there are some key limitations.
Source - Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Control
2023-06-20 - Research Publication - This paper presents an integrated framework for proactive HRC.
Source - Robust and Context-Aware Real-Time Collaborative Robot Handling via Dynamic Gesture Commands
2023-04-12 - Research Publication - To address these challenges, the authors introduce Conditional Collaborative Handling Process (CCHP) to encode a contextaware cobot handling policy and a procedure to learn such policy from human-human collaboration.
Source - Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation
2023-04-12 - Research Publication - The authors introduce Demo-EASE, a novel training framework using a dual-buffer architecture that stores both demonstrations and RL-generated experiences.
Source - Condition-based Design of Variable Impedance Controllers from User Demonstrations
2022-09-21 - Research Publication - This paper presents an approach to ensure conditions on Variable Impedance Controllers through the off-line tuning of the parameters involved in its description.
Source - Task-Agnostic Adaptation for Safe Human-Robot Handover
2022-09-20 - Research Publication - Human-robot interaction (HRI) is an important component to improve the flexibility of modern production lines. However, in real-world applications, the task (\ie the conditions that the robot needs to operate on, such as the environmental lighting condition, the human subjects to interact with, and the hardware platforms) may vary and it remains challenging to optimally and efficiently configure and adapt the robotic system under these changing tasks.
Source - Kinova Gemini: Interactive Robot Grasping with Visual Reasoning and Conversational AI
2022-09-03 - Research Publication - Kinova Gemini combines conversational dialogue and visual reasoning on a Kinova Gen3 lite robot for object retrieval and perception-based pick-and-place tasks.
Source - Contact-Implicit Trajectory Optimization with Hydroelastic Contact and iLQR
2022-02-28 - Research Publication - The study presents preliminary results suggesting that the Iterative Linear Quadratic Regulator (iLQR) algorithm together with the recently proposed pressure-field-based hydroelastic contact model enables reliable and physically realistic trajectory optimization through contact.
Source - Learn from Human Teams: a Probabilistic Solution to Real-Time Collaborative Robot Handling with Dynamic Gesture Commands
2021-12-11 - Research Publication - The study proposes a Real-Time Collaborative Robot Handling (RTCoHand) framework that allows the control of cobot via user-customized dynamic gestures.
Source - Learning Visual-Audio Representations for Voice-Controlled Robots
2021-09-07 - Research Publication - Inspired by sensorimotor theory, the authors propose a novel pipeline for task-oriented voice-controlled robots.
Source - Kinova Gen3-Lite manipulator inverse kinematics: optimal polynomial solution
2021-02-01 - Research Publication - A polynomial solution to the inverse kinematic problem of the Kinova Gen3 Lite robot is proposed in this paper.
Source - Real-Time Deep Learning Approach to Visual Servo Control and Grasp Detection for Autonomous Robotic Manipulation
2020-10-13 - Research Publication - The developed controller was able to achieve a millimeter accuracy in the final position considering a target object seen for the first time.
Source - vincentzhang/gen3-mujoco
Research Publication - MuJoCo model of the Kinova Gen3 robot.
Source
Resources
Media library
- Kinova Gen3 product view
image · Kinova Robotics
Source
Official Kinova product documentation, developer references and exact product media for the Gen3 ultra-lightweight robot.
- Gen3 product and configuration reference
WEB · Gen3 · Kinova Robotics
Source - Gen3 ultra-lightweight robot user guide
PDF · Gen3, revision R07 · Kinova Robotics
Source - Kortex API documentation
WEB · Gen3 Kortex API · Kinova Robotics
Source
Timeline
- SNC-Lavalin and Kinova sign collaboration for nuclear glovebox robotics
2020-07-17 - Partnership - SNC-Lavalin and Kinova signed a two-year agreement to deploy robotic solutions in the nuclear sector. SNC-Lavalin became Kinova's exclusive integrator for collaborative robots into operational gloveboxes at selected nuclear sites. The collaboration built on 2019 work showing a Kinova Gen3 arm deployed into an inactive glovebox.
Source
Context
Comparable Systems
- Franka Research 3
Franka Robotics - Collaborative Robot
- GoFa 12
ABB Robotics - Industrial Robot
- DOBOT Nova 5
Dobot - Industrial Cobot
- CRX-5iA
FANUC - Industrial Robot
- Rizon 4
Flexiv Robotics Ltd. - Industrial Cobot
- Rizon 4S
Flexiv Robotics Ltd. - Industrial Robot