Humanoid Robot
Humanoid robots, aiming to replicate human form and function, are a focus of intense robotics research. Current efforts concentrate on improving locomotion across challenging terrains using reinforcement learning and transformer models, developing more efficient whole-body control methods (including those driven by neural signals or leveraging passive dynamics), and enhancing human-robot interaction through imitation learning and natural language processing. These advancements are significant for both the robotics community, pushing the boundaries of control algorithms and AI, and for practical applications in areas like assistive care, disaster response, and human-robot collaboration.
Papers
Grounding Language Models in Autonomous Loco-manipulation Tasks
Jin Wang, Nikos Tsagarakis
Adaptive Non-linear Centroidal MPC with Stability Guarantees for Robust Locomotion of Legged Robots
Mohamed Elobaid, Giulio Turrisi, Lorenzo Rapetti, Giulio Romualdi, Stefano Dafarra, Tomohiro Kawakami, Tomohiro Chaki, Takahide Yoshiike, Claudio Semini, Daniele Pucci
Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation
Hassan Ali, Philipp Allgeuer, Carlo Mazzola, Giulia Belgiovine, Burak Can Kaplan, Stefan Wermter
Dual-arm Motion Generation for Repositioning Care based on Deep Predictive Learning with Somatosensory Attention Mechanism
Tamon Miyake, Namiko Saito, Tetsuya Ogata, Yushi Wang, Shigeki Sugano
NAS: N-step computation of All Solutions to the footstep planning problem
Jiayi Wang, Saeid Samadi, Hefan Wang, Pierre Fernbach, Olivier Stasse, Sethu Vijayakumar, Steve Tonneau
Flow Matching Imitation Learning for Multi-Support Manipulation
Quentin Rouxel (Inria), Andrea Ferrari (Inria), Serena Ivaldi (Inria), Jean-Baptiste Mouret (Inria)