Researchers present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation.
Resources
By Topic:
By Type:
High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measures
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...
Force Admittance Control of an Underactuated Gripper with Full-State Feedback
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...
Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners?
Researchers investigate how to leverage model-based planning and optimization to generate training data for contact-rich dexterous manipulation tasks.
ASHiTA: Automatic Scene-grounded Hierarchical Task Analysis
ASHiTA alternates LLM-assisted hierarchical task analysis, to generate the task breakdown, with task-driven 3D scene graph construction to generate a suitable representation of the environment.
Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans?
Researchers at the Institute examine the effectiveness of linear feedback controllers for contact-rich robotic manipulation, with differentiable simulations that use contact smoothing.
Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization
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...
LEGATO: Cross-Embodiment Imitation Using a Grasping Tool
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...
Continuously Improving Mobile Manipulation with Autonomous Real-World RL
We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision.
Jacta: A Versatile Planner for Learning Dexterous and Whole-Body Manipulation
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...
On-Robot Reinforcement Learning with Goal-Contrastive Rewards
Researchers at the RAI Institute propose GCR (Goal-Contrastive Rewards), a dense reward function learning method that can be trained on passive video demonstrations.
GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy
To enhance the generalization capabilities of Diffusion Policy, we introduce a novel framework that incorporates explicit spatial and semantic information via 3D semantic fields.