On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer

• URL: http://arxiv.org/abs/2312.03673v2
• Date: Mon, 29 Apr 2024 18:11:47 GMT
• Title: On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer
• Authors: Elie Aljalbout, Felix Frank, Maximilian Karl, Patrick van der Smagt,
• Abstract summary: We study the choice of action space in robot manipulation learning and sim-to-real transfer. We train over 250 reinforcement learning(RL) agents in simulated reaching and pushing tasks. The choice of spaces spans combinations of common action space design characteristics.
• Score: 6.1622717998840395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the choice of action space in robot manipulation learning and sim-to-real transfer. We define metrics that assess the performance, and examine the emerging properties in the different action spaces. We train over 250 reinforcement learning~(RL) agents in simulated reaching and pushing tasks, using 13 different control spaces. The choice of spaces spans combinations of common action space design characteristics. We evaluate the training performance in simulation and the transfer to a real-world environment. We identify good and bad characteristics of robotic action spaces and make recommendations for future designs. Our findings have important implications for the design of RL algorithms for robot manipulation tasks, and highlight the need for careful consideration of action spaces when training and transferring RL agents for real-world robotics.

Related papers

• Redundancy-aware Action Spaces for Robot Learning [17.961314026588987]
  Joint space and task space control are the two dominant action modes for controlling robot arms within the robot learning literature. This work analyses the criteria for designing action spaces for robot manipulation and introduces ER (End-effector Redundancy), a novel action space formulation. We present two implementations of ER, ERAngle (ERA) and ERJoint (ERJ), and we show that ERJ in particular demonstrates superior performance across multiple settings.
  arXiv  Detail & Related papers  (2024-06-06T15:08:41Z)
• Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment [24.93621734941354]
  This paper focuses on transferring control policies between robot manipulators with different morphology. Key insight is to project the state and action spaces of the source and target robots to a common latent space representation. We demonstrate sim-to-sim and sim-to-real manipulation policy transfer with source and target robots of different states, actions, and embodiments.
  arXiv  Detail & Related papers  (2024-06-04T05:00:24Z)
• Unsupervised Learning of Effective Actions in Robotics [0.9374652839580183]
  Current state-of-the-art action representations in robotics lack proper effect-driven learning of the robot's actions. We propose an unsupervised algorithm to discretize a continuous motion space and generate "action prototypes" We evaluate our method on a simulated stair-climbing reinforcement learning task.
  arXiv  Detail & Related papers  (2024-04-03T13:28:52Z)
• Learning Human-to-Robot Handovers from Point Clouds [63.18127198174958]
  We propose the first framework to learn control policies for vision-based human-to-robot handovers. We show significant performance gains over baselines on a simulation benchmark, sim-to-sim transfer and sim-to-real transfer.
  arXiv  Detail & Related papers  (2023-03-30T17:58:36Z)
• Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning [24.223788665601678]
  Two xArm6 robots solve the U-shape assembly task with a success rate of above90% in simulation, and 50% on real hardware without any additional real-world fine-tuning. Our results present a significant step forward for bi-arm capability on real hardware, and we hope our system can inspire future research on deep RL and Sim2Real transfer bi-manualpolicies.
  arXiv  Detail & Related papers  (2023-03-27T01:25:24Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)
• Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives [92.0321404272942]
  Reinforcement learning can be used to build general-purpose robotic systems. However, training RL agents to solve robotics tasks still remains challenging. In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy. We find that our simple change to the action interface substantially improves both the learning efficiency and task performance.
  arXiv  Detail & Related papers  (2021-10-28T17:59:30Z)
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation [99.2543521972137]
  ReLMoGen is a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. ReLMoGen shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.
  arXiv  Detail & Related papers  (2020-08-18T08:05:15Z)
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [62.22058066456076]
  Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks. RL does not work directly in the real-world, which is known as the sim-to-real transfer problem. We propose a method that learns on an observation space constructed by point clouds and environment randomization.
  arXiv  Detail & Related papers  (2020-07-27T17:46:59Z)
• SAPIEN: A SimulAted Part-based Interactive ENvironment [77.4739790629284]
  SAPIEN is a realistic and physics-rich simulated environment that hosts a large-scale set for articulated objects. We evaluate state-of-the-art vision algorithms for part detection and motion attribute recognition as well as demonstrate robotic interaction tasks.
  arXiv  Detail & Related papers  (2020-03-19T00:11:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.