Bridging the gap between learning-to-plan, motion primitives and safe reinforcement learning

P Kicki, D Tateo, P Liu, J Guenster, J Peters… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Trajectory planning under kinodynamic constraints is fundamental for advanced robotics
applications that require dexterous, reactive, and rapid skills in complex environments …

A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

P Liu, J Günster, N Funk, S Gröger… - Advances in …, 2025‏ - proceedings.neurips.cc
Abstract Machine learning methods have a groundbreaking impact in many application
domains, but their application on real robotic platforms is still limited. Despite the many …

Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning

J Günster, P Liu, J Peters, D Tateo - arxiv preprint arxiv:2409.12045, 2024‏ - arxiv.org
Safety is one of the key issues preventing the deployment of reinforcement learning
techniques in real-world robots. While most approaches in the Safe Reinforcement Learning …

Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees

D Kim, T Cho, S Han, H Chung… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
The field of risk-constrained reinforcement learning (RCRL) has been developed to
effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure …

Energy-based Contact Planning under Uncertainty for Robot Air Hockey

J Jankowski, A Marić, P Liu, D Tateo, J Peters… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Planning robot contact often requires reasoning over a horizon to anticipate outcomes,
making such planning problems computationally expensive. In this letter, we propose a …

ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning

D Kim, M Srouji, C Chen, J Zhang - arxiv preprint arxiv:2412.00396, 2024‏ - arxiv.org
Humanoid robots have significant gaps in their sensing and perception, making it hard to
perform motion planning in dense environments. To address this, we introduce ARMOR, a …

G-AlignNet: Geometry-Driven Quality Alignment for Robust Dynamical Systems Modeling

H Li, C XIAO, M Guo, Y Weng‏ - openreview.net
The Neural ODE family has shown promise in modeling complex systems but often assumes
consistent data quality, making them less effective in real-world applications with irregularly …