Search Results for author:
Found 35 papers, 17 papers with code
Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation for Efficient Synthesis and Verification
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.
PoCo: Policy Composition from and for Heterogeneous Robot Learning
Training general robotic policies from heterogeneous data for different tasks is a significant challenge.
Robot Fleet Learning via Policy Merging
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.
Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching
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.
Synthesizing Stable Reduced-Order Visuomotor Policies for Nonlinear Systems via Sums-of-Squares Optimization
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.
Smoothed Online Learning for Prediction in Piecewise Affine Systems
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.
Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?
We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system.
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?
Decentralized learning has been advocated and widely deployed to make efficient use of distributed datasets, with an extensive focus on supervised learning (SL) problems.
Elliptical Slice Sampling for Probabilistic Verification of Stochastic Systems with Signal Temporal Logic Specifications
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.
Learning Multi-Object Dynamics with Compositional Neural Radiance Fields
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.
Globally Convergent Policy Search over Dynamic Filters for Output Estimation
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.
Do Differentiable Simulators Give Better Policy Gradients?
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.
Learning Models as Functionals of Signed-Distance Fields for Manipulation Planning
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.
Shortest Paths in Graphs of Convex Sets
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
Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems
Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics.
FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis
Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent environments.
The Surprising Effectiveness of Linear Models for Visual Foresight in Object Pile Manipulation
In this paper, we tackle the problem of pushing piles of small objects into a desired target set using visual feedback.
Robotics
Self-Supervised Correspondence in Visuomotor Policy Learning
In this paper we explore using self-supervised correspondence for improving the generalization performance and sample efficiency of visuomotor policy learning.
kPAM-SC: Generalizable Manipulation Planning using KeyPoint Affordance and Shape Completion
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.
Connecting Touch and Vision via Cross-Modal Prediction
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.
SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction
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.
kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation
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
Linear Encodings for Polytope Containment Problems
This problem is rooted in computational convexity, and arises in applications such as verification and control of dynamical systems.
Optimization and Control Computational Geometry
FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization
Additionally, we present a simple and efficient twist parameterization that generalizes our method to the registration of articulated and deformable objects.
Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing.
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
In this paper, we propose to learn a particle-based simulator for complex control tasks.
Propagation Networks for Model-Based Control Under Partial Observation
There has been an increasing interest in learning dynamics simulators for model-based control.
Sampling-based Polytopic Trees for Approximate Optimal Control of Piecewise Affine Systems
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
LVIS: Learning from Value Function Intervals for Contact-Aware Robot Controllers
Guided policy search is a popular approach for training controllers for high-dimensional systems, but it has a number of pitfalls.
Robotics
Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation
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.
Evaluating Robustness of Neural Networks with Mixed Integer Programming
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.
LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes
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.
Funnel Libraries for Real-Time Robust Feedback Motion Planning
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.
Pushbroom Stereo for High-Speed Navigation in Cluttered Environments
We present a novel stereo vision algorithm that is capable of obstacle detection on a mobile-CPU processor at 120 frames per second.
Signal-to-Noise Ratio Analysis of Policy Gradient Algorithms
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.
