10 papers
Learning Unions of Convex Sets via Invertible Latent Decomposition for Path Planning
Taerim Yoon, Dongho Kang, Kisang Park +3
Collision-free path planning in cluttered, real-world environments relies on a representation of the collision-free space, and existing representations broadly fall into two catego…
Walk Like Dogs: Learning Steerable Imitation Controllers for Legged Robots from Unlabeled Motion Data
Dongho Kang, Jin Cheng, Fatemeh Zargarbashi +3
We present an imitation learning framework that extracts distinctive legged locomotion behaviors and transitions between them from unlabeled real-world motion data. By automaticall…
Teaching Robots Like Dogs: Learning Agile Navigation from Luring, Gesture, and Speech
Taerim Yoon, Dongho Kang, Jin Cheng +5
In this work, we aim to enable legged robots to learn how to interpret human social cues and produce appropriate behaviors through physical human guidance. However, learning throug…
Multi-Domain Motion Embedding: Expressive Real-Time Mimicry for Legged Robots
Matthias Heyrman, Chenhao Li, Victor Klemm +3
Effective motion representation is crucial for enabling robots to imitate expressive behaviors in real time, yet existing motion controllers often ignore inherent patterns in motio…
Whole-Body Inverse Dynamics MPC for Legged Loco-Manipulation
Lukas Molnar, Jin Cheng, Gabriele Fadini +3
Loco-manipulation demands coordinated whole-body motion to manipulate objects effectively while maintaining locomotion stability, presenting significant challenges for both plannin…
SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer
Yarden As, Chengrui Qu, Benjamin Unger +6
Deploying reinforcement learning (RL) safely in the real world is challenging, as policies trained in simulators must face the inevitable sim-to-real gap. Robust safe RL techniques…