no code implementations • 23 Mar 2024 • Allen Z. Ren, Jaden Clark, Anushri Dixit, Masha Itkina, Anirudha Majumdar, Dorsa Sadigh
We consider the problem of Embodied Question Answering (EQA), which refers to settings where an embodied agent such as a robot needs to actively explore an environment to gather information until it is confident about the answer to a question.
no code implementations • NeurIPS 2023 • Apoorva Sharma, Sushant Veer, Asher Hancock, Heng Yang, Marco Pavone, Anirudha Majumdar
To remedy this, recent work has proposed learning model and score function parameters using data to directly optimize the efficiency of the ICP prediction sets.
no code implementations • 5 Sep 2023 • Jensen Gao, Bidipta Sarkar, Fei Xia, Ted Xiao, Jiajun Wu, Brian Ichter, Anirudha Majumdar, Dorsa Sadigh
We incorporate this physically grounded VLM in an interactive framework with a large language model-based robotic planner, and show improved planning performance on tasks that require reasoning about physical object concepts, compared to baselines that do not leverage physically grounded VLMs.
no code implementations • 4 Jul 2023 • Allen Z. Ren, Anushri Dixit, Alexandra Bodrova, Sumeet Singh, Stephen Tu, Noah Brown, Peng Xu, Leila Takayama, Fei Xia, Jake Varley, Zhenjia Xu, Dorsa Sadigh, Andy Zeng, Anirudha Majumdar
Large language models (LLMs) exhibit a wide range of promising capabilities -- from step-by-step planning to commonsense reasoning -- that may provide utility for robots, but remain prone to confidently hallucinated predictions.
no code implementations • 26 Apr 2023 • Anirudha Majumdar
We seek to understand fundamental tradeoffs between the accuracy of prior information that a learner has on a given problem and its learning performance.
no code implementations • 9 Feb 2023 • Allen Z. Ren, Hongkai Dai, Benjamin Burchfiel, Anirudha Majumdar
Addressing this issue, we propose AdaptSim, a new task-driven adaptation framework for sim-to-real transfer that aims to optimize task performance in target (real) environments -- instead of matching dynamics between simulation and reality.
no code implementations • 27 Jun 2022 • Allen Z. Ren, Bharat Govil, Tsung-Yen Yang, Karthik Narasimhan, Anirudha Majumdar
Robust and generalized tool manipulation requires an understanding of the properties and affordances of different tools.
1 code implementation • 31 Jan 2022 • Anirudha Majumdar, Zhiting Mei, Vincent Pacelli
Our goal is to develop theory and algorithms for establishing fundamental limits on performance imposed by a robot's sensors for a given task.
no code implementations • 20 Jan 2022 • Kai-Chieh Hsu, Allen Z. Ren, Duy Phuong Nguyen, Anirudha Majumdar, Jaime F. Fisac
To improve safety, we apply a dual policy setup where a performance policy is trained using the cumulative task reward and a backup (safety) policy is trained by solving the Safety Bellman Equation based on Hamilton-Jacobi (HJ) reachability analysis.
no code implementations • 16 Nov 2021 • Ali Ekin Gurgen, Anirudha Majumdar, Sushant Veer
This paper presents an approach for learning motion planners that are accompanied with probabilistic guarantees of success on new environments that hold uniformly for any disturbance to the robot's dynamics within an admissible set.
no code implementations • 16 Nov 2021 • Abhinav Agarwal, Sushant Veer, Allen Z. Ren, Anirudha Majumdar
The key idea behind our approach is to utilize the generative model in order to implicitly specify a prior over policies.
1 code implementation • 13 Jul 2021 • Allen Z. Ren, Anirudha Majumdar
Our goal is to train control policies that generalize well to unseen environments.
1 code implementation • 25 Jun 2021 • Alec Farid, Sushant Veer, Divyanshu Pachisia, Anirudha Majumdar
Our goal is to perform out-of-distribution (OOD) detection, i. e., to detect when a robot is operating in environments drawn from a different distribution than the ones used to train the robot.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 26 Feb 2021 • Naman Agarwal, Elad Hazan, Anirudha Majumdar, Karan Singh
We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics.
1 code implementation • 19 Feb 2021 • Paula Gradu, John Hallman, Daniel Suo, Alex Yu, Naman Agarwal, Udaya Ghai, Karan Singh, Cyril Zhang, Anirudha Majumdar, Elad Hazan
We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite.
1 code implementation • NeurIPS 2021 • Alec Farid, Anirudha Majumdar
We are motivated by the problem of providing strong generalization guarantees in the context of meta-learning.
no code implementations • 12 Dec 2020 • Udaya Ghai, David Snyder, Anirudha Majumdar, Elad Hazan
We consider the problem of generating maximally adversarial disturbances for a given controller assuming only blackbox access to it.
no code implementations • 24 Oct 2020 • Christine Allen-Blanchette, Sushant Veer, Anirudha Majumdar, Naomi Ehrich Leonard
In this paper, we introduce a video prediction model where the equations of motion are explicitly constructed from learned representations of the underlying physical quantities.
1 code implementation • 17 Aug 2020 • Meghan Booker, Anirudha Majumdar
State-of-the-art approaches for controlling robots often use memory representations that are excessively rich for the task or rely on hand-crafted tricks for memory efficiency.
2 code implementations • 5 Aug 2020 • Allen Z. Ren, Sushant Veer, Anirudha Majumdar
Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies.
no code implementations • 16 Jul 2020 • Sushant Veer, Anirudha Majumdar
We present a novel algorithm -- convex natural evolutionary strategies (CoNES) -- for optimizing high-dimensional blackbox functions by leveraging tools from convex optimization and information geometry.
1 code implementation • 1 Jun 2020 • Anoopkumar Sonar, Vincent Pacelli, Anirudha Majumdar
A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training.
1 code implementation • 28 Feb 2020 • Sushant Veer, Anirudha Majumdar
This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i. e., environments unseen during training).
no code implementations • 4 Feb 2020 • Vincent Pacelli, Anirudha Majumdar
Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's state and rich sensor observations.
no code implementations • 14 Aug 2019 • Anirudha Majumdar, Georgina Hall, Amir Ali Ahmadi
Historically, scalability has been a major challenge to the successful application of semidefinite programming in fields such as machine learning, control, and robotics.
1 code implementation • 20 Sep 2018 • Vincent Pacelli, Anirudha Majumdar
We propose novel iterative algorithms for automatically synthesizing (offline) a task-driven representation (given in terms of a set of task-relevant variables (TRVs)) and a performant control policy that is a function of the TRVs.
Optimization and Control Robotics Systems and Control
1 code implementation • 11 Jun 2018 • Anirudha Majumdar, Alec Farid, Anoopkumar Sonar
The key technical idea behind our approach is to leverage tools from generalization theory in machine learning by exploiting a precise analogy (which we present in the form of a reduction) between generalization of control policies to novel environments and generalization of hypotheses in the supervised learning setting.
1 code implementation • 28 Nov 2017 • Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone
The literature on Inverse Reinforcement Learning (IRL) typically assumes that humans take actions in order to minimize the expected value of a cost function, i. e., that humans are risk neutral.
no code implementations • 30 Oct 2017 • Anirudha Majumdar, Marco Pavone
We discuss general representation theorems that precisely characterize the class of metrics that satisfy these axioms (referred to as distortion risk metrics), and provide instantiations that can be used in applications.
no code implementations • 9 Oct 2017 • Amir Ali Ahmadi, Anirudha Majumdar
In a recent note [8], the author provides a counterexample to the global convergence of what his work refers to as "the DSOS and SDSOS hierarchies" for polynomial optimization problems (POPs) and purports that this refutes claims in our extended abstract [4] and slides in [3].
no code implementations • 8 Jun 2017 • Amir Ali Ahmadi, Anirudha Majumdar
The reliance of this technique on large-scale semidefinite programs however, has limited the scale of problems to which it can be applied.
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.