6 papers
Efficient Real-World Online Reinforcement Learning for Robot Manipulation via Centralized Training and Critic Decomposition
Changhao Li, Yifang Zhang, Heng Zhang +6
Real-world online reinforcement learning (RL) provides a promising approach for training robotic manipulation policies directly in the physical world, avoiding the sim-to-real gap…
Learning Fault-Tolerant Locomotion with Adaptive Gait Timing
Giovanbattista Gravina, Luca Rossini, Carlo Rizzardo +2
Hardware failures require legged robots to rapidly reorganize coordination and gait timing to maintain stability and mobility. This is particularly challenging for larger quadruped…
KYON: Semi-Modular Wheel-Legged Quadruped With Agile Bimanual Capability
Luca Rossini, Arturo Laurenzi, Francesco Ruscelli +8
This paper presents KYON, a hybrid wheel-legged quadruped robot equipped with a bimanual upper body for loco-manipulation tasks. The platform features a semi-modular design with a…
RL-Augmented MPC for Non-Gaited Legged and Hybrid Locomotion
Andrea Patrizi, Carlo Rizzardo, Arturo Laurenzi +3
We propose a contact-explicit hierarchical architecture coupling Reinforcement Learning (RL) and Model Predictive Control (MPC), where a high-level RL agent provides gait and navig…
Vision-Language-Policy Model for Dynamic Robot Task Planning
Jin Wang, Kim Tien Ly, Jacques Cloete +3
Bridging the gap between natural language commands and autonomous execution in unstructured environments remains an open challenge for robotics. This requires robots to perceive an…
A Task-Driven, Planner-in-the-Loop Computational Design Framework for Modular Manipulators
Maolin Lei, Edoardo Romiti, Arturo Laurenzi +5
Modular manipulators composed of pre-manufactured and interchangeable modules offer high adaptability across diverse tasks. However, their deployment requires generating feasible m…