Search Results for author:
Found 32 papers, 12 papers with code
Explore until Confident: Efficient Exploration for Embodied Question Answering
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.
PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction
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.
Physically Grounded Vision-Language Models for Robotic Manipulation
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.
Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
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.
Fundamental Tradeoffs in Learning with Prior Information
We seek to understand fundamental tradeoffs between the accuracy of prior information that a learner has on a given problem and its learning performance.
AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer
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.
Leveraging Language for Accelerated Learning of Tool Manipulation
Robust and generalized tool manipulation requires an understanding of the properties and affordances of different tools.
Fundamental Limits for Sensor-Based Robot Control
Our goal is to develop theory and algorithms for establishing fundamental limits on performance imposed by a robot's sensors for a given task.
Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees
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.
Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data
The key idea behind our approach is to utilize the generative model in order to implicitly specify a prior over policies.
Learning Provably Robust Motion Planners Using Funnel Libraries
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.
Distributionally Robust Policy Learning via Adversarial Environment Generation
Our goal is to train control policies that generalize well to unseen environments.
Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning
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
A Regret Minimization Approach to Iterative Learning Control
We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics.
Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking
We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite.
Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability
We are motivated by the problem of providing strong generalization guarantees in the context of meta-learning.
Generating Adversarial Disturbances for Controller Verification
We consider the problem of generating maximally adversarial disturbances for a given controller assuming only blackbox access to it.
LagNetViP: A Lagrangian Neural Network for Video Prediction
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.
Learning to Actively Reduce Memory Requirements for Robot Control Tasks
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.
Generalization Guarantees for Imitation Learning
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.
CoNES: Convex Natural Evolutionary Strategies
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.
Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning
A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training.
Probably Approximately Correct Vision-Based Planning using Motion Primitives
This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i. e., environments unseen during training).
Learning Task-Driven Control Policies via Information Bottlenecks
Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's state and rich sensor observations.
A Survey of Recent Scalability Improvements for Semidefinite Programming with Applications in Machine Learning, Control, and Robotics
Historically, scalability has been a major challenge to the successful application of semidefinite programming in fields such as machine learning, control, and robotics.
Task-Driven Estimation and Control via Information Bottlenecks
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
PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments
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.
Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods
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.
How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics
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.
Response to "Counterexample to global convergence of DSOS and SDSOS hierarchies"
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].
DSOS and SDSOS Optimization: More Tractable Alternatives to Sum of Squares and Semidefinite Optimization
The reliance of this technique on large-scale semidefinite programs however, has limited the scale of problems to which it can be applied.
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.
