Search Results for author: Claire Tomlin

Found 35 papers, 8 papers with code

Unfamiliar Finetuning Examples Control How Language Models Hallucinate

no code implementations8 Mar 2024 Katie Kang, Eric Wallace, Claire Tomlin, Aviral Kumar, Sergey Levine

Large language models (LLMs) have a tendency to generate plausible-sounding yet factually incorrect responses, especially when queried on unfamiliar concepts.

Multiple-choice

Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximations

no code implementations15 Feb 2024 Jingqi Li, Anand Siththaranjan, Somayeh Sojoudi, Claire Tomlin, Andrea Bajcsy

Autonomous agents should be able to coordinate with other agents without knowing their intents ahead of time.

Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security

no code implementations18 Jan 2024 Marsalis Gibson, David Babazadeh, Claire Tomlin, Shankar Sastry

Even though image maps may contribute slightly to the prediction output of both models, this result reveals that rather than being robust to adversarial image perturbations, trajectory predictors are susceptible to image attacks.

Autonomous Driving Trajectory Prediction

Deep Neural Networks Tend To Extrapolate Predictably

1 code implementation2 Oct 2023 Katie Kang, Amrith Setlur, Claire Tomlin, Sergey Levine

Rather than extrapolating in arbitrary ways, we observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD.

Decision Making

Linking vision and motion for self-supervised object-centric perception

1 code implementation14 Jul 2023 Kaylene C. Stocking, Zak Murez, Vijay Badrinarayanan, Jamie Shotton, Alex Kendall, Claire Tomlin, Christopher P. Burgess

Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features.

Autonomous Driving Object

Scenario-Game ADMM: A Parallelized Scenario-Based Solver for Stochastic Noncooperative Games

no code implementations4 Apr 2023 Jingqi Li, Chih-Yuan Chiu, Lasse Peters, Fernando Palafox, Mustafa Karabag, Javier Alonso-Mora, Somayeh Sojoudi, Claire Tomlin, David Fridovich-Keil

To accommodate this, we decompose the approximated game into a set of smaller games with few constraints for each sampled scenario, and propose a decentralized, consensus-based ADMM algorithm to efficiently compute a generalized Nash equilibrium (GNE) of the approximated game.

Decision Making

Multi-Agent Reachability Calibration with Conformal Prediction

no code implementations2 Apr 2023 Anish Muthali, Haotian Shen, Sampada Deglurkar, Michael H. Lim, Rebecca Roelofs, Aleksandra Faust, Claire Tomlin

We investigate methods to provide safety assurances for autonomous agents that incorporate predictions of other, uncontrolled agents' behavior into their own trajectory planning.

Autonomous Driving Conformal Prediction +2

Multi-Task Imitation Learning for Linear Dynamical Systems

no code implementations1 Dec 2022 Thomas T. Zhang, Katie Kang, Bruce D. Lee, Claire Tomlin, Sergey Levine, Stephen Tu, Nikolai Matni

In particular, we consider a setting where learning is split into two phases: (a) a pre-training step where a shared $k$-dimensional representation is learned from $H$ source policies, and (b) a target policy fine-tuning step where the learned representation is used to parameterize the policy class.

Imitation Learning Representation Learning

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

no code implementations21 Jun 2022 Katie Kang, Paula Gradu, Jason Choi, Michael Janner, Claire Tomlin, Sergey Levine

Learned models and policies can generalize effectively when evaluated within the distribution of the training data, but can produce unpredictable and erroneous outputs on out-of-distribution inputs.

Density Estimation

Navigation between initial and desired community states using shortcuts

2 code implementations15 Apr 2022 Benjamin W. Blonder, Michael H. Lim, Zachary Sunberg, Claire Tomlin

Using several empirical datasets, we show that (1) non-brute-force navigation is only possible between some state pairs, (2) shortcuts exist between many state pairs; and (3) changes in abundance and richness are the strongest predictors of shortcut existence, independent of dataset and algorithm choices.

Management

Inducing Structure in Reward Learning by Learning Features

1 code implementation18 Jan 2022 Andreea Bobu, Marius Wiggert, Claire Tomlin, Anca D. Dragan

To get around this issue, recent deep Inverse Reinforcement Learning (IRL) methods learn rewards directly from the raw state but this is challenging because the robot has to implicitly learn the features that are important and how to combine them, simultaneously.

Incorporating Data Uncertainty in Object Tracking Algorithms

no code implementations22 Sep 2021 Anish Muthali, Forrest Laine, Claire Tomlin

However, for detections generated from neural-network processed camera inputs, these measurement error statistics are not sufficient to represent the primary source of errors, namely a dissimilarity between run-time sensor input and the training data upon which the detector was trained.

Object Object Tracking

Testing for Typicality with Respect to an Ensemble of Learned Distributions

no code implementations11 Nov 2020 Forrest Laine, Claire Tomlin

In particular, we propose training an ensemble of density models, considering data to be anomalous if the data is anomalous with respect to any member of the ensemble.

Anomaly Detection

DeepReach: A Deep Learning Approach to High-Dimensional Reachability

1 code implementation4 Nov 2020 Somil Bansal, Claire Tomlin

Its advantages include compatibility with general nonlinear system dynamics, formal treatment of bounded disturbances, and the ability to deal with state and input constraints.

Autonomous Driving Vocal Bursts Intensity Prediction

Expert Selection in High-Dimensional Markov Decision Processes

no code implementations26 Oct 2020 Vicenc Rubies-Royo, Eric Mazumdar, Roy Dong, Claire Tomlin, S. Shankar Sastry

In this work we present a multi-armed bandit framework for online expert selection in Markov decision processes and demonstrate its use in high-dimensional settings.

Vocal Bursts Intensity Prediction

Feature Expansive Reward Learning: Rethinking Human Input

1 code implementation23 Jun 2020 Andreea Bobu, Marius Wiggert, Claire Tomlin, Anca D. Dragan

When the correction cannot be explained by these features, recent work in deep Inverse Reinforcement Learning (IRL) suggests that the robot could ask for task demonstrations and recover a reward defined over the raw state space.

Visual Navigation Among Humans with Optimal Control as a Supervisor

1 code implementation20 Mar 2020 Varun Tolani, Somil Bansal, Aleksandra Faust, Claire Tomlin

Videos describing our approach and experiments, as well as a demo of HumANav are available on the project website.

Navigate Social Navigation +1

Combining Optimal Control and Learning for Visual Navigation in Novel Environments

no code implementations6 Mar 2019 Somil Bansal, Varun Tolani, Saurabh Gupta, Jitendra Malik, Claire Tomlin

Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories.

Robot Navigation Visual Navigation

Regression-based Inverter Control for Decentralized Optimal Power Flow and Voltage Regulation

no code implementations20 Feb 2019 Oscar Sondermeijer, Roel Dobbe, Daniel Arnold, Claire Tomlin, Tamás Keviczky

Electronic power inverters are capable of quickly delivering reactive power to maintain customer voltages within operating tolerances and to reduce system losses in distribution grids.

regression

Fast Neural Network Verification via Shadow Prices

no code implementations19 Feb 2019 Vicenc Rubies-Royo, Roberto Calandra, Dusan M. Stipanovic, Claire Tomlin

To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation.

Collision Avoidance

A Successive-Elimination Approach to Adaptive Robotic Sensing

no code implementations27 Sep 2018 Esther Rolf, David Fridovich-Keil, Max Simchowitz, Benjamin Recht, Claire Tomlin

We study an adaptive source seeking problem, in which a mobile robot must identify the strongest emitter(s) of a signal in an environment with background emissions.

Trajectory Planning

Towards Distributed Energy Services: Decentralizing Optimal Power Flow with Machine Learning

no code implementations14 Jun 2018 Roel Dobbe, Oscar Sondermeijer, David Fridovich-Keil, Daniel Arnold, Duncan Callaway, Claire Tomlin

We consider distribution systems with multiple controllable Distributed Energy Resources (DERs) and present a data-driven approach to learn control policies for each DER to reconstruct and mimic the solution to a centralized OPF problem from solely locally available information.

BIG-bench Machine Learning

Countering Feedback Delays in Multi-Agent Learning

no code implementations NeurIPS 2017 Zhengyuan Zhou, Panayotis Mertikopoulos, Nicholas Bambos, Peter W. Glynn, Claire Tomlin

We consider a model of game-theoretic learning based on online mirror descent (OMD) with asynchronous and delayed feedback information.

On Identification of Distribution Grids

1 code implementation5 Nov 2017 Omid Ardakanian, Vincent W. S. Wong, Roel Dobbe, Steven H. Low, Alexandra von Meier, Claire Tomlin, Ye Yuan

Large-scale integration of distributed energy resources into residential distribution feeders necessitates careful control of their operation through power flow analysis.

A Sequential Approximation Framework for Coded Distributed Optimization

no code implementations24 Oct 2017 Jingge Zhu, Ye Pu, Vipul Gupta, Claire Tomlin, Kannan Ramchandran

As an application of the results, we demonstrate solving optimization problems using a sequential approximation approach, which accelerates the algorithm in a distributed system with stragglers.

Distributed Optimization

Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach

no code implementations NeurIPS 2017 Roel Dobbe, David Fridovich-Keil, Claire Tomlin

Learning cooperative policies for multi-agent systems is often challenged by partial observability and a lack of coordination.

A Multi-Armed Bandit Approach for Online Expert Selection in Markov Decision Processes

no code implementations18 Jul 2017 Eric Mazumdar, Roy Dong, Vicenç Rúbies Royo, Claire Tomlin, S. Shankar Sastry

We formulate a multi-armed bandit (MAB) approach to choosing expert policies online in Markov decision processes (MDPs).

Systems and Control

Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games

no code implementations NeurIPS 2016 Maximilian Balandat, Walid Krichene, Claire Tomlin, Alexandre Bayen

We study a general adversarial online learning problem, in which we are given a decision set X' in a reflexive Banach space X and a sequence of reward vectors in the dual space of X.

Recursive Regression with Neural Networks: Approximating the HJI PDE Solution

no code implementations8 Nov 2016 Vicenç Rubies Royo, Claire Tomlin

The majority of methods used to compute approximations to the Hamilton-Jacobi-Isaacs partial differential equation (HJI PDE) rely on the discretization of the state space to perform dynamic programming updates.

regression

Inverse Power Flow Problem

no code implementations21 Oct 2016 Ye Yuan, Steven Low, Omid Ardakanian, Claire Tomlin

We show that the admittance matrix can be uniquely identified from a sequence of measurements corresponding to different steady states when every node in the system is equipped with a measurement device, and a Kron-reduced admittance matrix can be determined even if some nodes in the system are not monitored (hidden nodes).

Minimizing Regret on Reflexive Banach Spaces and Learning Nash Equilibria in Continuous Zero-Sum Games

no code implementations3 Jun 2016 Maximilian Balandat, Walid Krichene, Claire Tomlin, Alexandre Bayen

Under the assumption of uniformly continuous rewards, we obtain explicit anytime regret bounds in a setting where the decision set is the set of probability distributions on a compact metric space $S$ whose Radon-Nikodym derivatives are elements of $L^p(S)$ for some $p > 1$.

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