Robotics Domain
Robotics research currently focuses on enhancing robot autonomy, safety, and dexterity, particularly in unstructured environments. Key areas include developing robust control algorithms (like Model Predictive Control and reinforcement learning), improving perception through advanced sensor fusion and generative models, and creating more efficient and adaptable robot designs. These advancements are driving progress in diverse applications such as agriculture, healthcare, and manufacturing, ultimately aiming to create more capable and reliable robots for a wider range of tasks.
Papers
Toward Information Theoretic Active Inverse Reinforcement Learning
Ondrej Bajgar, Sid William Gould, Rohan Narayan Langford Mitta, Jonathon Liu, Oliver Newcombe, Jack Golden
Predicate Invention from Pixels via Pretrained Vision-Language Models
Ashay Athalye, Nishanth Kumar, Tom Silver, Yichao Liang, Tomás Lozano-Pérez, Leslie Pack Kaelbling
URDF+: An Enhanced URDF for Robots with Kinematic Loops
Matthew Chignoli, Jean-Jacques Slotine, Patrick M. Wensing, Sangbae Kim
Development of CPS Platform for Autonomous Construction
Yuichiro Kasahara, Kota Akinari, Tomoya Kouno, Noriko Sano, Taro Abe, Genki Yamauchi, Daisuke Endo, Takeshi Hashimoto, Keiji Nagatani, Ryo Kurazume