Active Embodiment Identification with Reinforcement Learning for Legged Robots

2026-05-08 · Nico Bohlinger, Jan Peters arxiv

We present an active embodiment identification method for legged robots that jointly learns information-seeking behavior and explicit embodiment prediction. Using a history-augmented URMA architecture, the method infers joint-level and global embodiment parameters through interaction with the environment in simulation across different morphologies.

📄 PDF Abstract BibTeX arXiv:2605.08020

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion

2024-09-10 · Nico Bohlinger, Grzegorz Czechmanowski, Maciej Krupka, Piotr Kicki 외

Deep Reinforcement Learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is st…

All Deep Reinforcement Learning reinforcement-learning Reinforcement Learning

Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization

2025-09-02 · Nico Bohlinger, Jan Peters arxiv

We present a single, general locomotion policy trained on a diverse collection of 50 legged robots. By combining an improved embodiment-aware architecture (URMAv2) with a performance-based curriculum for extreme Embodime…

KING: Embodiment-Aware Kinematic Graph Neural Network for Unified Motion Representation of Legged and Wheeled Robots

2026-08-02 · Taku Okawara, Aoki Takanose, Kenji Koide, Shuji Oishi 외 arxiv

Kinematic models provide reliable motion constraints for odometry estimation in featureless environments, where exteroceptive sensing degrades and IMU integration drifts. Learning-based kinematic models can achieve more …

Graph Neural Network Few-Shot Learning

Adversarial joint attacks on legged robots

2022-05-20 · Takuto Otomo, Hiroshi Kera, Kazuhiko Kawamoto

We address adversarial attacks on the actuators at the joints of legged robots trained by deep reinforcement learning. The vulnerability to the joint attacks can significantly impact the safety and robustness of legged r…

Deep Reinforcement Learning OpenAI Gym reinforcement-learning Reinforcement Learning+1

Adversarial Body Shape Search for Legged Robots

2022-05-20 · Takaaki Azakami, Hiroshi Kera, Kazuhiko Kawamoto

We propose an evolutionary computation method for an adversarial attack on the length and thickness of parts of legged robots by deep reinforcement learning. This attack changes the robot body shape and interferes with w…

Adversarial Attack Deep Reinforcement Learning OpenAI Gym