Publications

Synthesize contact-rich grasps for multi-fingered hands via differentiable simulation

We present a pipeline to learn simulators from depth or RGB video. The “URDF” of a mechanism is reconstructed, and the simulation parameters are inferred through Bayesian inference.

Reducing the reality gap through a Bayesian inference algorithm that leverages massive GPU parallelism and differentiable simulators.

This paper presents and discusses algorithms, hardware, and software architecture developed by the TEAM CoSTAR (Collaborative …

We introduce a differentiable simulator for robotic cutting. It achieves highly accurate predictions of the knife forces, optimizes cutting actions & more!
Best Student Paper at RSS 2021

Differentiable simulators provide an avenue for closing the sim2real gap by enabling the use of efficient, gradient-based optimization …

Differentiable simulators provide an avenue for closing the sim-to-real gap by enabling the use of efficient, gradient-based …

Employing robots in the real world to perform a large variety of tasks remains a great challenge to current perception, planning and control algorithms. Various specialized representations, such as for mapping or localization, have been proposed which are typically used in fixed pipelines that fuse perception, planning and control.

We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical …

Planning smooth and energy-efficient motions for wheeled mobile robots is a central task in applications ranging from autonomous …

We present a strategy for simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than …

Simultaneous Localization and Mapping (SLAM) in large-scale, unknown, and complex subterranean environments is a challenging problem. …

A key ingredient to achieving intelligent behavior is physical understanding that equips robots with the ability to reason about the …

Light Detection and Ranging (LIDAR) sensors play an important role in the perception stack of autonomous robots, supplying mapping and …

Accurate simulations allow modern machine learning techniques to be applied to robotics problems, with sample-collection runtimes …

Intelligent agents need a physical understanding of the world to predict the impact of their actions in the future. While …

Representing the environment is a fundamental task in enabling robots to act autonomously in unknown environments. In this work, we …

Personal robots assisting humans must perform complex manipulation tasks that are typically difficult to specify in traditional motion …

Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful …

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill …

Autonomous navigation of intelligent physical systems largely depend on the ability of the system to generate an accurate map of its …

Planning smooth trajectories is important for the safe, efficient and comfortable operation of mobile robots, such as wheeled robots …

Planning safe, high-speed trajectories in unknown environments remains a major roadblock on the way toward achieving fast autonomous …

Occupancy grids are a common framework in robotics for creating a spatial map of the environment. Traditional grid mapping algorithms …

Studies of market structure and product market competition are important in many disciplines, such as economics, finance, accounting …

Automatically diagnosing a complex system containing heterogeneous hard- and software components is a challenging task. To analyze the …