Robotics

DiffPhyCon uses diffusion models to generate near-optimal control sequences for complex physical systems, outperforming existing methods by simultaneously optimizing a generative energy function and c…

Quantum algorithm achieves super-quadratic speedup for large-scale linear control, offering a novel approach to address the computational challenges of optimizing complex dynamical systems.

DG-SLAM achieves robust real-time visual SLAM in dynamic scenes using 3D Gaussian splatting and a novel hybrid pose optimization, significantly outperforming existing methods.

Boosting Human-AI teamwork via interactive, explainable AI!

CooHOI: A two-phase learning framework enables physically simulated characters to perform cooperative object transportation tasks naturally and efficiently, overcoming the limitations of existing meth…

Projected Diffusion Models (PDM) revolutionizes generative modeling by directly incorporating constraints into the sampling process, ensuring high-fidelity outputs that strictly adhere to predefined c…

CLOVER: A closed-loop visuomotor framework using generative visual plans & feedback mechanisms achieves state-of-the-art results in long-horizon robotic manipulation tasks.

BricksRL: A low-cost, open-source platform democratizes robotics and reinforcement learning research using LEGO, enabling accessible real-world experiments.

This paper introduces Belief-State Query (BSQ) constraints for user-aligned planning in partially observable settings, providing algorithms with guaranteed user alignment and computational feasibility…

BAKU: A simple transformer enables efficient multi-task robot policy learning, achieving 91% success on real-world tasks with limited data.

AdaFlow: a novel imitation learning framework boasts fast inference and diverse action generation via variance-adaptive flow-based policies, significantly outperforming existing methods.

ActiveNGF achieves superior robotic grasping by using a Neural Graspness Field to model scene grasp distribution online, enabling efficient camera movement and improved grasp pose detection.

Researchers enhanced transformer models for inertial pose estimation by introducing a Sequence Structure Module, leveraging inherent fixed-length sequence structures for improved accuracy and steadine…