Search Results for author: Katherine Driggs-Campbell

Found 37 papers, 15 papers with code

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art

no code implementations25 Mar 2024 Neeloy Chakraborty, Melkior Ornik, Katherine Driggs-Campbell

The rise of foundation models trained on multiple tasks with impressively large datasets from a variety of fields has led researchers to believe that these models may provide common sense reasoning that existing planners are missing.

Common Sense Reasoning Decision Making +1

Towards Provable Log Density Policy Gradient

no code implementations3 Mar 2024 Pulkit Katdare, Anant Joshi, Katherine Driggs-Campbell

In this work, we argue that this residual term is significant and correcting for it could potentially improve sample-complexity of reinforcement learning methods.

Policy Gradient Methods reinforcement-learning

D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Manipulation

no code implementations28 Sep 2023 YiXuan Wang, Zhuoran Li, Mingtong Zhang, Katherine Driggs-Campbell, Jiajun Wu, Li Fei-Fei, Yunzhu Li

These fields capture the dynamics of the underlying 3D environment and encode both semantic features and instance masks.

Marginalized Importance Sampling for Off-Environment Policy Evaluation

no code implementations4 Sep 2023 Pulkit Katdare, Nan Jiang, Katherine Driggs-Campbell

This paper proposes a new approach to evaluate the real-world performance of agent policies prior to deploying them in the real world.

Reinforcement Learning (RL)

PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems

no code implementations1 Aug 2023 Aamir Hasan, Neeloy Chakraborty, Haonan Chen, Jung-Hoon Cho, Cathy Wu, Katherine Driggs-Campbell

To this end, we develop a co-operative advisory system based on PC policies with a novel driver trait conditioned Personalized Residual Policy, PeRP.

DRAGON: A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding

1 code implementation13 Jul 2023 Shuijing Liu, Aamir Hasan, Kaiwen Hong, Runxuan Wang, Peixin Chang, Zachary Mizrachi, Justin Lin, D. Livingston McPherson, Wendy A. Rogers, Katherine Driggs-Campbell

Motivated by recent advances in visual-language grounding and semantic navigation, we propose DRAGON, a guiding robot powered by a dialogue system and the ability to associate the environment with natural language.

Dynamic-Resolution Model Learning for Object Pile Manipulation

no code implementations29 Jun 2023 YiXuan Wang, Yunzhu Li, Katherine Driggs-Campbell, Li Fei-Fei, Jiajun Wu

Prior works typically assume representation at a fixed dimension or resolution, which may be inefficient for simple tasks and ineffective for more complicated tasks.

Model Predictive Control Object

Conveying Autonomous Robot Capabilities through Contrasting Behaviour Summaries

no code implementations1 Apr 2023 Peter Du, Surya Murthy, Katherine Driggs-Campbell

In this paper we present an adaptive search method for efficiently generating contrasting behaviour summaries with support for continuous state and action spaces.

Adaptive Failure Search Using Critical States from Domain Experts

no code implementations1 Apr 2023 Peter Du, Katherine Driggs-Campbell

Adaptive Stress Testing (AST) is one such method that poses the problem of failure search as a Markov decision process and uses reinforcement learning techniques to find high probability failures.

Autonomous Driving

Towards Co-operative Congestion Mitigation

no code implementations17 Feb 2023 Aamir Hasan, Neeloy Chakraborty, Cathy Wu, Katherine Driggs-Campbell

The effects of traffic congestion are widespread and are an impedance to everyday life.

Occlusion-Aware Crowd Navigation Using People as Sensors

1 code implementation2 Oct 2022 Ye-Ji Mun, Masha Itkina, Shuijing Liu, Katherine Driggs-Campbell

To the best of our knowledge, this work is the first to use social occlusion inference for crowd navigation.

Autonomous Navigation Collision Avoidance

CoCAtt: A Cognitive-Conditioned Driver Attention Dataset (Supplementary Material)

no code implementations8 Jul 2022 Yuan Shen, Niviru Wijayaratne, Pranav Sriram, Aamir Hasan, Peter Du, Katherine Driggs-Campbell

In addition, the attention data in our dataset is captured in both manual and autopilot modes using eye-tracking devices of different resolutions.

Driver Attention Monitoring

Meta-path Analysis on Spatio-Temporal Graphs for Pedestrian Trajectory Prediction

1 code implementation27 Feb 2022 Aamir Hasan, Pranav Sriram, Katherine Driggs-Campbell

We employ MESRNN for pedestrian trajectory prediction, utilizing these meta-path based features to capture the relationships between the trajectories of pedestrians at different points in time and space.

Action Recognition Pedestrian Trajectory Prediction +2

Off Environment Evaluation Using Convex Risk Minimization

1 code implementation21 Dec 2021 Pulkit Katdare, Shuijing Liu, Katherine Driggs-Campbell

We also show that the our method is able to estimate performance of a 7 DOF robotic arm using the simulator and remotely collected data from the robot in the real world.

Reinforcement Learning (RL)

Learning to Navigate Intersections with Unsupervised Driver Trait Inference

1 code implementation14 Sep 2021 Shuijing Liu, Peixin Chang, Haonan Chen, Neeloy Chakraborty, Katherine Driggs-Campbell

Then, we use this trait representation to learn a policy for an autonomous vehicle to navigate through a T-intersection with deep reinforcement learning.

Autonomous Navigation Navigate +2

Multi-Agent Variational Occlusion Inference Using People as Sensors

1 code implementation5 Sep 2021 Masha Itkina, Ye-Ji Mun, Katherine Driggs-Campbell, Mykel J. Kochenderfer

We propose an occlusion inference method that characterizes observed behaviors of human agents as sensor measurements, and fuses them with those from a standard sensor suite.

Autonomous Vehicles Sensor Fusion

Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction

1 code implementation15 Jul 2021 Zhe Huang, Ruohua Li, Kazuki Shin, Katherine Driggs-Campbell

Multi-pedestrian trajectory prediction is an indispensable element of autonomous systems that safely interact with crowds in unstructured environments.

Pedestrian Trajectory Prediction Trajectory Prediction

Building Mental Models through Preview of Autopilot Behaviors

no code implementations12 Apr 2021 Yuan Shen, Niviru Wijayaratne, Katherine Driggs-Campbell

Effective human-vehicle collaboration requires an appropriate un-derstanding of vehicle behavior for safety and trust.

Future prediction

Improving the Feasibility of Moment-Based Safety Analysis for Stochastic Dynamics

no code implementations11 Apr 2021 Peter Du, Katherine Driggs-Campbell, Roy Dong

We then reformulate the constraints of the optimization to mitigate the computational limitations associated with an increase in state dimensionality.

Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments

1 code implementation15 Dec 2020 Tianchen Ji, Sri Theja Vuppala, Girish Chowdhary, Katherine Driggs-Campbell

To achieve high-levels of autonomy, modern robots require the ability to detect and recover from anomalies and failures with minimal human supervision.

Anomaly Detection

Monte-Carlo Tree Search for Policy Optimization

no code implementations23 Dec 2019 Xiaobai Ma, Katherine Driggs-Campbell, Zongzhang Zhang, Mykel J. Kochenderfer

Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points.

reinforcement-learning Reinforcement Learning (RL)

Online monitoring for safe pedestrian-vehicle interactions

no code implementations12 Oct 2019 Peter Du, Zhe Huang, Tianqi Liu, Ke Xu, Qichao Gao, Hussein Sibai, Katherine Driggs-Campbell, Sayan Mitra

As autonomous systems begin to operate amongst humans, methods for safe interaction must be investigated.

Robotics Multiagent Systems Signal Processing

Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation

no code implementations2 Aug 2019 Anthony Corso, Peter Du, Katherine Driggs-Campbell, Mykel J. Kochenderfer

Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems.

Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving

no code implementations6 May 2019 Carl-Johan Hoel, Katherine Driggs-Campbell, Krister Wolff, Leo Laine, Mykel J. Kochenderfer

This paper introduces a general framework for tactical decision making, which combines the concepts of planning and learning, in the form of Monte Carlo tree search and deep reinforcement learning.

Autonomous Driving Decision Making +1

Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning

1 code implementation28 Apr 2019 Masha Itkina, Katherine Driggs-Campbell, Mykel J. Kochenderfer

A key challenge for autonomous driving is safe trajectory planning in cluttered, urban environments with dynamic obstacles, such as pedestrians, bicyclists, and other vehicles.

Autonomous Driving Representation Learning

Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning

no code implementations8 Mar 2019 Xiaobai Ma, Katherine Driggs-Campbell, Mykel J. Kochenderfer

To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment.

Autonomous Driving reinforcement-learning +1

EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning

no code implementations22 Jul 2018 Kunal Menda, Katherine Driggs-Campbell, Mykel J. Kochenderfer

While imitation learning is often used in robotics, the approach frequently suffers from data mismatch and compounding errors.

Imitation Learning

DropoutDAgger: A Bayesian Approach to Safe Imitation Learning

no code implementations18 Sep 2017 Kunal Menda, Katherine Driggs-Campbell, Mykel J. Kochenderfer

While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors.

Imitation Learning

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