Jan Peters
5 papers · Latest:
Active Embodiment Identification with Reinforcement Learning for Legged Robots
A method using reinforcement learning to actively identify legged robot embodiment parameters via interaction.
Evaluation of an Actuated Spine in Agile Quadruped Locomotion
This paper empirically shows that an actuated spine significantly enhances the agility and obstacle negotiation capabilities of quadruped robots.
AssistDLO: Assistive Teleoperation for Deformable Linear Object Manipulation
AssistDLO is an assistive teleoperation framework for manipulating deformable linear objects, combining state estimation, visual assistance, and geometry-aware shared autonomy.
RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects
RopeDreamer uses a kinematic recurrent state space model with quaternions to robustly predict flexible deformable linear object dynamics, preventing non-physical deformations.
Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control
This paper proposes a behavior-constrained RL framework with receding-horizon credit assignment to learn high-performance, expert-consistent control policies.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.