Search Results for author: Gaurav S. Sukhatme

Found 46 papers, 17 papers with code

Interactive Differentiable Simulation

2 code implementations26 May 2019 Eric Heiden, David Millard, Hejia Zhang, Gaurav S. Sukhatme

While learning-based models of the environment dynamics have contributed to significant improvements in sample efficiency compared to model-free reinforcement learning algorithms, they typically fail to generalize to system states beyond the training data, while often grounding their predictions on non-interpretable latent variables.

Model Predictive Control reinforcement-learning +1

Augmenting Differentiable Simulators with Neural Networks to Close the Sim2Real Gap

1 code implementation12 Jul 2020 Eric Heiden, David Millard, Erwin Coumans, Gaurav S. Sukhatme

We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation.

NeuralSim: Augmenting Differentiable Simulators with Neural Networks

2 code implementations9 Nov 2020 Eric Heiden, David Millard, Erwin Coumans, Yizhou Sheng, Gaurav S. Sukhatme

Differentiable simulators provide an avenue for closing the sim-to-real gap by enabling the use of efficient, gradient-based optimization algorithms to find the simulation parameters that best fit the observed sensor readings.

Robotics

Inferring Articulated Rigid Body Dynamics from RGBD Video

1 code implementation20 Mar 2022 Eric Heiden, Ziang Liu, Vibhav Vineet, Erwin Coumans, Gaurav S. Sukhatme

Being able to reproduce physical phenomena ranging from light interaction to contact mechanics, simulators are becoming increasingly useful in more and more application domains where real-world interaction or labeled data are difficult to obtain.

Contact mechanics Inverse Rendering

QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control

1 code implementation15 Jun 2023 Zhehui Huang, Sumeet Batra, Tao Chen, Rahul Krupani, Tushar Kumar, Artem Molchanov, Aleksei Petrenko, James A. Preiss, Zhaojing Yang, Gaurav S. Sukhatme

In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality.

Reinforcement Learning (RL)

Experimental Comparison of Global Motion Planning Algorithms for Wheeled Mobile Robots

1 code implementation7 Mar 2020 Eric Heiden, Luigi Palmieri, Kai O. Arras, Gaurav S. Sukhatme, Sven Koenig

Planning smooth and energy-efficient motions for wheeled mobile robots is a central task for applications ranging from autonomous driving to service and intralogistic robotics.

Autonomous Driving Motion Planning

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges

1 code implementation10 Nov 2021 Yizhou Zhao, Kaixiang Lin, Zhiwei Jia, Qiaozi Gao, Govind Thattai, Jesse Thomason, Gaurav S. Sukhatme

However, current simulators for Embodied AI (EAI) challenges only provide simulated indoor scenes with a limited number of layouts.

Indoor Scene Synthesis Scene Generation

DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following

2 code implementations27 Feb 2022 Xiaofeng Gao, Qiaozi Gao, Ran Gong, Kaixiang Lin, Govind Thattai, Gaurav S. Sukhatme

Language-guided Embodied AI benchmarks requiring an agent to navigate an environment and manipulate objects typically allow one-way communication: the human user gives a natural language command to the agent, and the agent can only follow the command passively.

Instruction Following Navigate

Sampling-Based Motion Planning on Sequenced Manifolds

1 code implementation3 Jun 2020 Peter Englert, Isabel M. Rayas Fernández, Ragesh K. Ramachandran, Gaurav S. Sukhatme

We address the problem of planning robot motions in constrained configuration spaces where the constraints change throughout the motion.

Robotics Computational Geometry

Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors

2 code implementations11 Mar 2019 Artem Molchanov, Tao Chen, Wolfgang Hönig, James A. Preiss, Nora Ayanian, Gaurav S. Sukhatme

Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation.

Robotics

Learning Manifolds for Sequential Motion Planning

1 code implementation13 Jun 2020 Isabel M. Rayas Fernández, Giovanni Sutanto, Peter Englert, Ragesh K. Ramachandran, Gaurav S. Sukhatme

Motion planning with constraints is an important part of many real-world robotic systems.

Robotics Computational Geometry

Learning Deformable Object Manipulation from Expert Demonstrations

1 code implementation20 Jul 2022 Gautam Salhotra, I-Chun Arthur Liu, Marcus Dominguez-Kuhne, Gaurav S. Sukhatme

We test DMfD on a set of representative manipulation tasks for a 1-dimensional rope and a 2-dimensional cloth from the SoftGym suite of tasks, each with state and image observations.

Deformable Object Manipulation General Reinforcement Learning +1

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation

1 code implementation11 Nov 2021 I-Chun Arthur Liu, Shagun Uppal, Gaurav S. Sukhatme, Joseph J. Lim, Peter Englert, Youngwoon Lee

Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations.

Imitation Learning Motion Planning +3

Adaptive Sampling using POMDPs with Domain-Specific Considerations

1 code implementation23 Sep 2021 Gautam Salhotra, Christopher E. Denniston, David A. Caron, Gaurav S. Sukhatme

We find that by using knowledge of the number of rollouts allocated, the agent can more effectively choose actions to explore.

A Spatio-Temporal Representation for the Orienteering Problem with Time-Varying Profits

no code implementations24 Nov 2016 Zhibei Ma, Kai Yin, Lantao Liu, Gaurav S. Sukhatme

Different from most existing works where the profits are assumed to be static, in this work we investigate a variant that has arbitrary time-dependent profits.

Informative Planning and Online Learning with Sparse Gaussian Processes

no code implementations24 Sep 2016 Kai-Chieh Ma, Lantao Liu, Gaurav S. Sukhatme

A big challenge in environmental monitoring is the spatiotemporal variation of the phenomena to be observed.

Gaussian Processes

Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills

no code implementations29 Sep 2018 Hejia Zhang, Eric Heiden, Stefanos Nikolaidis, Joseph J. Lim, Gaurav S. Sukhatme

Personal robots assisting humans must perform complex manipulation tasks that are typically difficult to specify in traditional motion planning pipelines, where multiple objectives must be met and the high-level context be taken into consideration.

Motion Planning

Soft Value Iteration Networks for Planetary Rover Path Planning

no code implementations ICLR 2018 Max Pflueger, Ali Agha, Gaurav S. Sukhatme

In order to deal with complex terrain observations and policy learning, we propose a value iteration recurrence, referred to as the soft value iteration network (SVIN).

Motion Planning

A Solution to Time-Varying Markov Decision Processes

no code implementations3 May 2016 Lantao Liu, Gaurav S. Sukhatme

We consider a decision-making problem where the environment varies both in space and time.

Decision Making

Resilient Coverage: Exploring the Local-to-Global Trade-off

no code implementations3 Oct 2019 Ragesh K. Ramachandran, Lifeng Zhou James A. Preiss, Gaurav S. Sukhatme

We propose a centralized control framework to select suitable robots from a heterogeneous pool and place them at appropriate locations to monitor a region for events of interest.

Physics-based Simulation of Continuous-Wave LIDAR for Localization, Calibration and Tracking

no code implementations3 Dec 2019 Eric Heiden, Ziang Liu, Ragesh K. Ramachandran, Gaurav S. Sukhatme

Light Detection and Ranging (LIDAR) sensors play an important role in the perception stack of autonomous robots, supplying mapping and localization pipelines with depth measurements of the environment.

Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics

no code implementations22 Jan 2020 David Millard, Eric Heiden, Shubham Agrawal, Gaurav S. Sukhatme

A key ingredient to achieving intelligent behavior is physical understanding that equips robots with the ability to reason about the effects of their actions in a dynamic environment.

Model Predictive Control

Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning

no code implementations21 Apr 2020 Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme, Sergey Levine, Chelsea Finn, Karol Hausman

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments.

Continual Learning reinforcement-learning +2

Plan-Space State Embeddings for Improved Reinforcement Learning

no code implementations30 Apr 2020 Max Pflueger, Gaurav S. Sukhatme

We show how these embedding spaces can then be used as an augmentation to the robot state in reinforcement learning problems.

reinforcement-learning Reinforcement Learning (RL)

Confidence-rich grid mapping

no code implementations29 Jun 2020 Ali-akbar Agha-mohammadi, Eric Heiden, Karol Hausman, Gaurav S. Sukhatme

Representing the environment is a fundamental task in enabling robots to act autonomously in unknown environments.

Motion Planning

Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments

no code implementations22 Oct 2020 Jun Yamada, Youngwoon Lee, Gautam Salhotra, Karl Pertsch, Max Pflueger, Gaurav S. Sukhatme, Joseph J. Lim, Peter Englert

In contrast, motion planners use explicit models of the agent and environment to plan collision-free paths to faraway goals, but suffer from inaccurate models in tasks that require contacts with the environment.

reinforcement-learning Reinforcement Learning (RL) +1

Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation

no code implementations18 Sep 2021 Eric Heiden, Christopher E. Denniston, David Millard, Fabio Ramos, Gaurav S. Sukhatme

We address the latter problem of estimating parameters through a Bayesian inference approach that approximates a posterior distribution over simulation parameters given real sensor measurements.

Bayesian Inference Code Generation

Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems

no code implementations25 Sep 2021 Amanda Prorok, Matthew Malencia, Luca Carlone, Gaurav S. Sukhatme, Brian M. Sadler, Vijay Kumar

In this survey article, we analyze how resilience is achieved in networks of agents and multi-robot systems that are able to overcome adversity by leveraging system-wide complementarity, diversity, and redundancy - often involving a reconfiguration of robotic capabilities to provide some key ability that was not present in the system a priori.

A Simple Approach to Continual Learning by Transferring Skill Parameters

no code implementations19 Oct 2021 K. R. Zentner, Ryan Julian, Ujjwal Puri, Yulun Zhang, Gaurav S. Sukhatme

We take a fresh look at this problem, by considering a setting in which the robot is limited to storing that knowledge and experience only in the form of learned skill policies.

Continual Learning

Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation

no code implementations ICML Workshop LifelongML 2020 Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme, Sergey Levine, Chelsea Finn, Karol Hausman

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments, but most robot learning systems today are deployed as fixed policies which do not adapt after deployment.

Continual Learning Robotic Grasping

CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation

no code implementations30 Nov 2022 Vishnu Sashank Dorbala, Gunnar Sigurdsson, Robinson Piramuthu, Jesse Thomason, Gaurav S. Sukhatme

Our results on the coarse-grained instruction following task of REVERIE demonstrate the navigational capability of CLIP, surpassing the supervised baseline in terms of both success rate (SR) and success weighted by path length (SPL).

Instruction Following Object Recognition +1

OpenD: A Benchmark for Language-Driven Door and Drawer Opening

no code implementations10 Dec 2022 Yizhou Zhao, Qiaozi Gao, Liang Qiu, Govind Thattai, Gaurav S. Sukhatme

We introduce OPEND, a benchmark for learning how to use a hand to open cabinet doors or drawers in a photo-realistic and physics-reliable simulation environment driven by language instruction.

RREx-BoT: Remote Referring Expressions with a Bag of Tricks

no code implementations30 Jan 2023 Gunnar A. Sigurdsson, Jesse Thomason, Gaurav S. Sukhatme, Robinson Piramuthu

Armed with this intuition, using only a generic vision-language scoring model with minor modifications for 3d encoding and operating in an embodied environment, we demonstrate an absolute performance gain of 9. 84% on remote object grounding above state of the art models for REVERIE and of 5. 04% on FAO.

Object Object Localization

LEMMA: Learning Language-Conditioned Multi-Robot Manipulation

no code implementations2 Aug 2023 Ran Gong, Xiaofeng Gao, Qiaozi Gao, Suhaila Shakiah, Govind Thattai, Gaurav S. Sukhatme

We introduce a benchmark for LanguagE-Conditioned Multi-robot MAnipulation (LEMMA) focused on task allocation and long-horizon object manipulation based on human language instructions in a tabletop setting.

LEMMA Robot Manipulation

HyperPPO: A scalable method for finding small policies for robotic control

no code implementations28 Sep 2023 Shashank Hegde, Zhehui Huang, Gaurav S. Sukhatme

We demonstrate that the neural policies estimated by HyperPPO are capable of decentralized control of a Crazyflie2. 1 quadrotor.

Guaranteed Trust Region Optimization via Two-Phase KL Penalization

no code implementations8 Dec 2023 K. R. Zentner, Ujjwal Puri, Zhehui Huang, Gaurav S. Sukhatme

Then, we show that introducing a "fixup" phase is sufficient to guarantee a trust region is enforced on every policy update while adding fewer than 5% additional gradient steps in practice.

Computational Efficiency Reinforcement Learning (RL)

From Words to Routes: Applying Large Language Models to Vehicle Routing

no code implementations16 Mar 2024 Zhehui Huang, Guangyao Shi, Gaurav S. Sukhatme

The success of LLMs in these tasks leads us to wonder: What is the ability of LLMs to solve vehicle routing problems (VRPs) with natural language task descriptions?

Code Generation Text-to-Code Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.