no code implementations • 23 Aug 2023 • Thomas Power, Dmitry Berenson
We present Constrained Stein Variational Trajectory Optimization (CSVTO), an algorithm for performing trajectory optimization with constraints on a set of trajectories in parallel.
no code implementations • 23 May 2023 • Mark Van der Merwe, Youngsun Wi, Dmitry Berenson, Nima Fazeli
Representing the object geometry and contact with the environment implicitly allows a single model to predict contact patches of varying complexity.
1 code implementation • 14 May 2023 • Sheng Zhong, Nima Fazeli, Dmitry Berenson
Rather than attempting to estimate the true pose of the object, which is not tractable without a large number of contacts, we seek to estimate a plausible set of poses which obey the constraints imposed by the sensor data.
1 code implementation • 9 Mar 2023 • Jiayi Pan, Glen Chou, Dmitry Berenson
We evaluate our approach on three existing LTL/natural language datasets and show that we can translate natural language commands at 75\% accuracy with far less human data ($\le$12 annotations).
no code implementations • 14 Jun 2022 • Glen Chou, Necmiye Ozay, Dmitry Berenson
We present a motion planning algorithm for a class of uncertain control-affine nonlinear systems which guarantees runtime safety and goal reachability when using high-dimensional sensor measurements (e. g., RGB-D images) and a learned perception module in the feedback control loop.
no code implementations • 10 May 2022 • Thomas Power, Dmitry Berenson
We propose a Model Predictive Control (MPC) method for collision-free navigation that uses amortized variational inference to approximate the distribution of optimal control sequences by training a normalizing flow conditioned on the start, goal and environment.
no code implementations • 8 Dec 2021 • Glen Chou, Hao Wang, Dmitry Berenson
We propose a method for learning constraints represented as Gaussian processes (GPs) from locally-optimal demonstrations.
no code implementations • 18 Apr 2021 • Glen Chou, Necmiye Ozay, Dmitry Berenson
We derive a trajectory tracking error bound for a contraction-based controller that is subjected to this model error, and then learn a controller that optimizes this tracking bound.
1 code implementation • 1 Apr 2021 • Andrew Price, Kun Huang, Dmitry Berenson
In this work, we propose Multihypothesis Segmentation Tracking (MST), a novel method for volumetric segmentation in changing scenes, which allows scene ambiguity to be tracked and our estimates to be adjusted over time as we interact with the scene.
no code implementations • 4 Feb 2021 • Thomas Power, Dmitry Berenson
We use these images to train a perception model that estimates the simple model state from observations of the complex system online.
1 code implementation • 18 Nov 2020 • Brad Saund, Dmitry Berenson
We propose PSSNet, a network architecture for generating diverse plausible 3D reconstructions from a single 2. 5D depth image.
no code implementations • 9 Nov 2020 • Glen Chou, Necmiye Ozay, Dmitry Berenson
We present a method for learning to satisfy uncertain constraints from demonstrations.
1 code implementation • 1 Nov 2020 • YiXuan Wang, Dale McConachie, Dmitry Berenson
In order to manipulate a deformable object, such as rope or cloth, in unstructured environments, robots need a way to estimate its current shape.
1 code implementation • 23 Oct 2020 • Sheng Zhong, Zhenyuan Zhang, Nima Fazeli, Dmitry Berenson
We propose an approach to online model adaptation and control in the challenging case of hybrid and discontinuous dynamics where actions may lead to difficult-to-escape "trap" states, under a given controller.
no code implementations • 18 Oct 2020 • Craig Knuth, Glen Chou, Necmiye Ozay, Dmitry Berenson
Our method imposes the feedback law existence as a constraint in a sampling-based planner, which returns a feedback policy around a nominal plan ensuring that, if the Lipschitz constant estimate is valid, the true system is safe during plan execution, reaches the goal, and is ultimately invariant in a small set about the goal.
no code implementations • 3 Jun 2020 • Glen Chou, Necmiye Ozay, Dmitry Berenson
We present a method for learning multi-stage tasks from demonstrations by learning the logical structure and atomic propositions of a consistent linear temporal logic (LTL) formula.
no code implementations • 25 Jan 2020 • Glen Chou, Necmiye Ozay, Dmitry Berenson
We present an algorithm for learning parametric constraints from locally-optimal demonstrations, where the cost function being optimized is uncertain to the learner.
no code implementations • 8 Oct 2019 • Glen Chou, Necmiye Ozay, Dmitry Berenson
We present a scalable algorithm for learning parametric constraints in high dimensions from safe expert demonstrations.
no code implementations • 20 Jul 2019 • Andrew Price, Linyi Jin, Dmitry Berenson
Object search -- the problem of finding a target object in a cluttered scene -- is essential to solve for many robotics applications in warehouse and household environments.
no code implementations • 17 Dec 2018 • Glen Chou, Dmitry Berenson, Necmiye Ozay
We also provide theoretical analysis on what subset of the constraint can be learnable from safe demonstrations.
no code implementations • 29 Mar 2017 • Dale McConachie, Dmitry Berenson
The key contribution of this paper is to formulate the task as a Multi-Armed Bandit problem, with each arm representing a model of the deformable object.
no code implementations • 21 Jan 2016 • Nikolaus Correll, Kostas E. Bekris, Dmitry Berenson, Oliver Brock, Albert Causo, Kris Hauser, Kei Okada, Alberto Rodriguez, Joseph M. Romano, Peter R. Wurman
This paper presents a overview of the inaugural Amazon Picking Challenge along with a summary of a survey conducted among the 26 participating teams.
Robotics