首页|Evaluating the Effect of State and Action Selection on In-Hand Manipulation Performance for Transferability

Evaluating the Effect of State and Action Selection on In-Hand Manipulation Performance for Transferability

扫码查看
原文链接
  • NETL
  • NSTL
  • IEEE
Reinforcement learning (RL) has demonstrated success across multiple robotic grasping and manipulation tasks. However, for RL to be widely applicable, policies must be able to transfer across the sim-to-real gap, and transfer to hand geometries that they are not trained on. Methods such as domain randomization and domain adaptation only partially help with bridging these gaps. In this letter, we explore the impact of state and action space selection on transferability across both the sim-to-real gap and across different hand geometries. Using two exemplar manipulation tasks we demonstrate that state and action space selection significantly affect the overall performance of a policy and its robustness to both types of transfer. We also show that, for both types of transfer, a reduced state space that avoids hand specific information is preferable, even when it provides less information than a full state space.

HandsRobotsTrainingGeometryReinforcement learningTransfer learningGraspingKinematicsHardwareGrippers

Nigel Swenson、Jeremiah Goddard、Xiaoli Fern、Ravi Balasubramanian、Cindy Grimm

展开 >

College of Engineering, Robotics Department, Oregon State University, Corvallis, OR, USA

College of Engineering, Robotics Department, Oregon State University, Corvallis, OR, USA|College of Engineering, Electrical Engineering and Computer Science Department, Oregon State University, Corvallis, OR, USA

2025

10.1109/LRA.2025.3558699

IEEE robotics and automation letters

IEEE robotics and automation letters

ISSN：
年,卷(期)：2025.10(6)
  • 27