1 code implementation • 11 Apr 2024 • Lujie Yang, Hongkai Dai, Zhouxing Shi, Cho-Jui Hsieh, Russ Tedrake, huan zhang
The flexibility and efficiency of our framework allow us to demonstrate Lyapunov-stable output feedback control with synthesized NN-based controllers and NN-based observers with formal stability guarantees, for the first time in literature.
no code implementations • 4 Feb 2024 • Lirui Wang, Jialiang Zhao, Yilun Du, Edward H. Adelson, Russ Tedrake
Training general robotic policies from heterogeneous data for different tasks is a significant challenge.
1 code implementation • 2 Oct 2023 • Lirui Wang, Kaiqing Zhang, Allan Zhou, Max Simchowitz, Russ Tedrake
We show that FLEET-MERGE consolidates the behavior of policies trained on 50 tasks in the Meta-World environment, with good performance on nearly all training tasks at test time.
no code implementations • 24 Jun 2023 • H. J. Terry Suh, Glen Chou, Hongkai Dai, Lujie Yang, Abhishek Gupta, Russ Tedrake
However, in order to apply them effectively in offline optimization paradigms such as offline Reinforcement Learning (RL) or Imitation Learning (IL), we require a more careful consideration of how uncertainty estimation interplays with first-order methods that attempt to minimize them.
no code implementations • 24 Apr 2023 • Glen Chou, Russ Tedrake
To solve this problem approximately, we propose two approaches: the first solves a sequence of sum-of-squares optimization problems to iteratively improve a policy which is provably-stable by construction, while the second directly performs gradient-based optimization on the parameters of the polynomial policy, and its closed-loop stability is verified a posteriori.
no code implementations • NeurIPS 2023 • Adam Block, Max Simchowitz, Russ Tedrake
The problem of piecewise affine (PWA) regression and planning is of foundational importance to the study of online learning, control, and robotics, where it provides a theoretically and empirically tractable setting to study systems undergoing sharp changes in the dynamics.
no code implementations • 30 Dec 2022 • Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra
We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system.
1 code implementation • 20 Oct 2022 • Lirui Wang, Kaiqing Zhang, Yunzhu Li, Yonglong Tian, Russ Tedrake
Decentralized learning has been advocated and widely deployed to make efficient use of distributed datasets, with an extensive focus on supervised learning (SL) problems.
no code implementations • 28 Feb 2022 • Guy Scher, Sadra Sadraddini, Russ Tedrake, Hadas Kress-Gazit
Central to our approach is a method for efficient and rejection-free sampling of signals from a Gaussian distribution such that satisfy or violate a given STL formula.
no code implementations • 24 Feb 2022 • Danny Driess, Zhiao Huang, Yunzhu Li, Russ Tedrake, Marc Toussaint
We present a method to learn compositional multi-object dynamics models from image observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and graph neural networks.
no code implementations • 23 Feb 2022 • Jack Umenberger, Max Simchowitz, Juan C. Perdomo, Kaiqing Zhang, Russ Tedrake
In this paper, we provide a new perspective on this challenging problem based on the notion of $\textit{informativity}$, which intuitively requires that all components of a filter's internal state are representative of the true state of the underlying dynamical system.
no code implementations • 2 Feb 2022 • H. J. Terry Suh, Max Simchowitz, Kaiqing Zhang, Russ Tedrake
Differentiable simulators promise faster computation time for reinforcement learning by replacing zeroth-order gradient estimates of a stochastic objective with an estimate based on first-order gradients.
no code implementations • 2 Oct 2021 • Danny Driess, Jung-Su Ha, Marc Toussaint, Russ Tedrake
We show that representing objects as signed-distance fields not only enables to learn and represent a variety of models with higher accuracy compared to point-cloud and occupancy measure representations, but also that SDF-based models are suitable for optimization-based planning.
1 code implementation • 27 Jan 2021 • Tobia Marcucci, Jack Umenberger, Pablo A. Parrilo, Russ Tedrake
Given a graph, the shortest-path problem requires finding a sequence of edges with minimum cumulative length that connects a source vertex to a target vertex.
Robot Navigation Discrete Mathematics Optimization and Control
no code implementations • NeurIPS 2020 • Aman Sinha, Matthew O'Kelly, Russ Tedrake, John Duchi
Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics.
1 code implementation • ICML 2020 • Aman Sinha, Matthew O'Kelly, Hongrui Zheng, Rahul Mangharam, John Duchi, Russ Tedrake
Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent environments.
no code implementations • 21 Feb 2020 • H. J. Terry Suh, Russ Tedrake
In this paper, we tackle the problem of pushing piles of small objects into a desired target set using visual feedback.
Robotics
1 code implementation • 16 Sep 2019 • Peter Florence, Lucas Manuelli, Russ Tedrake
In this paper we explore using self-supervised correspondence for improving the generalization performance and sample efficiency of visuomotor policy learning.
no code implementations • 16 Sep 2019 • Wei Gao, Russ Tedrake
Using the proposed hybrid object representation, we formulate the manipulation task as a motion planning problem which encodes both the object target configuration and physical feasibility for a category of objects.
1 code implementation • CVPR 2019 • Yunzhu Li, Jun-Yan Zhu, Russ Tedrake, Antonio Torralba
To connect vision and touch, we introduce new tasks of synthesizing plausible tactile signals from visual inputs as well as imagining how we interact with objects given tactile data as input.
1 code implementation • 30 Apr 2019 • Wei Gao, Russ Tedrake
We contribute a dense SLAM system that takes a live stream of depth images as input and reconstructs non-rigid deforming scenes in real time, without templates or prior models.
no code implementations • 15 Mar 2019 • Lucas Manuelli, Wei Gao, Peter Florence, Russ Tedrake
However, representing an object with a parameterized transformation defined on a fixed template cannot capture large intra-category shape variation, and specifying a target pose at a category level can be physically infeasible or fail to accomplish the task -- e. g. knowing the pose and size of a coffee mug relative to some canonical mug is not sufficient to successfully hang it on a rack by its handle.
Robotics
1 code implementation • 12 Mar 2019 • Sadra Sadraddini, Russ Tedrake
This problem is rooted in computational convexity, and arises in applications such as verification and control of dynamical systems.
Optimization and Control Computational Geometry
1 code implementation • CVPR 2019 • Wei Gao, Russ Tedrake
Additionally, we present a simple and efficient twist parameterization that generalizes our method to the registration of articulated and deformable objects.
1 code implementation • NeurIPS 2018 • Matthew O'Kelly, Aman Sinha, Hongseok Namkoong, John Duchi, Russ Tedrake
While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing.
no code implementations • ICLR 2019 • Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B. Tenenbaum, Antonio Torralba
In this paper, we propose to learn a particle-based simulator for complex control tasks.
1 code implementation • 28 Sep 2018 • Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, Russ Tedrake
There has been an increasing interest in learning dynamics simulators for model-based control.
1 code implementation • 25 Sep 2018 • Sadra Sadraddini, Russ Tedrake
Piecewise affine (PWA) systems are widely used to model highly nonlinear behaviors such as contact dynamics in robot locomotion and manipulation.
Systems and Control Robotics Optimization and Control
1 code implementation • 16 Sep 2018 • Robin Deits, Twan Koolen, Russ Tedrake
Guided policy search is a popular approach for training controllers for high-dimensional systems, but it has a number of pitfalls.
Robotics
3 code implementations • 22 Jun 2018 • Peter R. Florence, Lucas Manuelli, Russ Tedrake
In this paper we present Dense Object Nets, which build on recent developments in self-supervised dense descriptor learning, as a consistent object representation for visual understanding and manipulation.
6 code implementations • ICLR 2019 • Vincent Tjeng, Kai Xiao, Russ Tedrake
The computational speedup allows us to verify properties on convolutional networks with an order of magnitude more ReLUs than networks previously verified by any complete verifier.
1 code implementation • 15 Jul 2017 • Pat Marion, Peter R. Florence, Lucas Manuelli, Russ Tedrake
We use an RGBD camera to collect video of a scene from multiple viewpoints and leverage existing reconstruction techniques to produce a 3D dense reconstruction.
no code implementations • 15 Jan 2016 • Anirudha Majumdar, Russ Tedrake
We consider the problem of generating motion plans for a robot that are guaranteed to succeed despite uncertainty in the environment, parametric model uncertainty, and disturbances.
no code implementations • 26 Jul 2014 • Andrew J. Barry, Russ Tedrake
We present a novel stereo vision algorithm that is capable of obstacle detection on a mobile-CPU processor at 120 frames per second.
no code implementations • NeurIPS 2008 • John W. Roberts, Russ Tedrake
Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the estimate of the gradient.