mlsanityData to 7 Oct 2026

Assistive Gym: A Physics Simulation Framework for Assistive Robotics

arXiv 1910.04700 ↗First posted 10 Oct 2019cs.RO cs.AI cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

Autonomous robots have the potential to serve as versatile caregivers that improve quality of life for millions of people worldwide. Yet, conducting research in this area presents numerous challenges, including the risks of physical interaction between people and robots. Physics simulations have been used to optimize and train robots for physical assistance, but have typically focused on a single task. In this paper, we present Assistive Gym, an open source physics simulation framework for assistive robots that models multiple tasks. It includes six simulated environments in which a robotic manipulator can attempt to assist a person with activities of daily living (ADLs): itch scratching, drinking, feeding, body manipulation, dressing, and bathing. Assistive Gym models a person's physical capabilities and preferences for assistance, which are used to provide a reward function. We present baseline policies trained using reinforcement learning for four different commercial robots in the six environments. We demonstrate that modeling human motion results in better assistance and we compare the performance of different robots. Overall, we show that Assistive Gym is a promising tool for assistive robotics research.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 11; 2023: 8; 2024: 7; 2025: 4; 2026: 4.

44 papers.

Sort:

By area:

  1. 2022Causal Confusion and Reward Misidentification in Preference-Based Reward Learningcited by 52
  2. 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
  3. 2021Interesting Object, Curious Agent: Learning Task-Agnostic Explorationcited by 38
  4. 2023Learning Human-to-Robot Handovers from Point Cloudscited by 34
  5. 2021Context-Aware Safe Reinforcement Learning for Non-Stationary Environmentscited by 33
  6. 2021Unsupervised Learning of Visual 3D Keypoints for Controlcited by 30
  7. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 27
  8. 2023ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environmentcited by 22
  9. 2021BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Imagecited by 20
  10. 2023Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Modelscited by 20
  11. 2021VisuoSpatial Foresight for Physical Sequential Fabric Manipulationcited by 18
  12. 2022HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handoverscited by 15
32 more
  1. 2022Learning Visuo-Haptic Skewering Strategies for Robot-Assisted Feedingcited by 15
  2. 2021On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learningcited by 14
  3. 2022Distributed Reinforcement Learning for Robot Teams: A Reviewcited by 11
  4. 2022Learning Representations that Enable Generalization in Assistive Taskscited by 11
  5. 2021Comparing Popular Simulation Environments in the Scope of Robotics and Reinforcement Learningcited by 10
  6. 2022EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamicscited by 10
  7. 2022ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learningcited by 8
  8. 2023Surrogate Assisted Generation of Human-Robot Interaction Scenarioscited by 8
  9. 2021Functional optimal transport: map estimation and domain adaptation for functional datacited by 7
  10. 2022Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactionscited by 5
  11. 2024A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motionscited by 4
  12. 2024DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learningcited by 3
  13. 2021DASH: Modularized Human Manipulation Simulation with Vision and Language for Embodied AIcited by 2
  14. 2023Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?cited by 2
  15. 2025Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motionscited by 2
  16. 2021Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learningcited by 1
  17. 2023Quantifying Assistive Robustness Via the Natural-Adversarial Frontiercited by 1
  18. 2023"Do it my way!": Impact of Customizations on Trust perceptions in Human-Robot Collaborationcited by 1
  19. 2024A Generalized Acquisition Function for Preference-based Reward Learningcited by 1
  20. 2025Inversely Learning Transferable Rewards via Abstracted Statescited by 1
  21. 2025MoDeSuite: Robot Learning Task Suite for Benchmarking Mobile Manipulation with Deformable Objectscited by 1
  22. 2026Embodied Human Simulation for Quantitative Design and Analysis of Interactive Roboticscited by 1
  23. 2022Concurrent Policy Blending and System Identification for Generalized Assistive Controlcited by 0
  24. 2022Improving Assistive Robotics with Deep Reinforcement Learningcited by 0
  25. 2023A Novel Variational Lower Bound for Inverse Reinforcement Learningcited by 0
  26. 2024Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Taskscited by 0
  27. 2024Reducing Risk for Assistive Reinforcement Learning Policies with Diffusion Modelscited by 0
  28. 2024Autonomous Quilt Spreading for Caregiving Robotscited by 0
  29. 2025Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Roboticscited by 0
  30. 2026ConTraIRL: Factorized Contrastive Abstractions for Transferable IRLcited by 0
  31. 2026VERAGMIL: Virtual Environment for Scooping Granular Foods with Imitation Learning Modelscited by 0
  32. 2026Dressing in Motion: A Human Motion-Aware Diffusion Policy for Robot-Assisted Dressingcited by 0