2 papers
cs.RO2026
Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments
Bastien Muraccioli, Alice Cariou, Pierre-Alexandre Leziart +4
Reinforcement Learning (RL) has demonstrated remarkable capabilities for solving complex robotic control problems, but its lack of safety guarantees severely limits deployment on h…
cs.RO2024
The Kinetics Observer: A Tightly Coupled Estimator for Legged Robots
Arnaud Demont, Mehdi Benallegue, Abdelaziz Benallegue +5
In this paper, we propose the "Kinetics Observer", a novel estimator addressing the challenge of state estimation for legged robots using proprioceptive sensors (encoders, IMU and…