Researchers present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation.
We’ve opened a free, hands-on robot lab for the summer! Plan your visit.
Researchers present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation.
This work presents an overview of the technical details behind a high-performance reinforcement learning policy deployment with the Spot RL Researcher Development Kit for low-level...
To move closer to the goal of next-generation hardware design capable of more human-like manipulation, researchers at the Institute have developed a new type of...
Researchers at the Institute examine the effectiveness of linear feedback controllers for contact-rich robotic manipulation, with differentiable simulations that use contact smoothing.
Researchers present a low-cost data generation pipeline that integrates physics-based simulation, human demonstrations, and model-based planning to efficiently generate large-scale, high-quality datasets for contact-rich robotic...
Cross-embodiment imitation learning enables policies trained on specific embodiments to transfer across different robots, unlocking the potential for large-scale imitation learning that is both cost-effective...
We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision.
Robotic manipulation is challenging and data-driven approaches typically require large amounts of data or expert demonstrations. Therefore, we introduce a motion planner for dexterous and...
Researchers at the RAI Institute propose GCR (Goal-Contrastive Rewards), a dense reward function learning method that can be trained on passive video demonstrations.
To enhance the generalization capabilities of Diffusion Policy, we introduce a novel framework that incorporates explicit spatial and semantic information via 3D semantic fields.
Scene representation is a crucial design choice in robotic manipulation systems. An ideal representation is expected to be 3D, dynamic, and semantic to meet the...
Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning.