138 citations · 402 across the 159 of their papers we have counts for
36 papers · 1 filter
Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering
Francois Chaubard, Duncan Eddy, Mykel J. Kochenderfer
We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization. Traditional distributed data-parallel stochastic gradien…
More than Marketing? On the Information Value of AI Benchmarks for Practitioners
Amelia Hardy, Anka Reuel, Kiana Jafari Meimandi +6
Public AI benchmark results are widely broadcast by model developers as indicators of model quality within a growing and competitive market. However, these advertised scores do not…
Failure Probability Estimation for Black-Box Autonomous Systems using State-Dependent Importance Sampling Proposals
Harrison Delecki, Sydney M. Katz, Mykel J. Kochenderfer
Estimating the probability of failure is a critical step in developing safety-critical autonomous systems. Direct estimation methods such as Monte Carlo sampling are often impracti…
Efficient Multiagent Planning via Shared Action Suggestions
Dylan M. Asmar, Mykel J. Kochenderfer
Decentralized partially observable Markov decision processes with communication (Dec-POMDP-Com) provide a framework for multiagent decision making under uncertainty, but the NEXP-c…
Sliced Distribution Matching based on Cumulative Distribution Functions with Applications to Control
Alexandros E. Tzikas, Arec Jamgochian, Nazim Kemal Ure +2
Computing the similarity between two probability distributions is a recurring theme across control. We introduce a unified family of distances between the probability distributions…
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
Anka Reuel, Amelia Hardy, Chandler Smith +3
AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attr…
SayComply: Grounding Field Robotic Tasks in Operational Compliance through Retrieval-Based Language Models
Muhammad Fadhil Ginting, Dong-Ki Kim, Sung-Kyun Kim +4
This paper addresses the problem of task planning for robots that must comply with operational manuals in real-world settings. Task planning under these constraints is essential fo…
Multi-scale Generative Modeling for Fast Sampling
Xiongye Xiao, Shixuan Li, Luzhe Huang +6
While working within the spatial domain can pose problems associated with ill-conditioned scores caused by power-law decay, recent advances in diffusion-based generative models hav…
Optimal Control of Mechanical Ventilators with Learned Respiratory Dynamics
Isaac Ronald Ward, Dylan M. Asmar, Mansur Arief +2
Deciding on appropriate mechanical ventilator management strategies significantly impacts the health outcomes for patients with respiratory diseases. Acute Respiratory Distress Syn…
Responsible AI in the Global Context: Maturity Model and Survey
Anka Reuel, Patrick Connolly, Kiana Jafari Meimandi +4
Responsible AI (RAI) has emerged as a major focus across industry, policymaking, and academia, aiming to mitigate the risks and maximize the benefits of AI, both on an organization…
Semi-Markovian Planning to Coordinate Aerial and Maritime Medical Evacuation Platforms
Mahdi Al-Husseini, Kyle H. Wray, Mykel J. Kochenderfer
The transfer of patients between two aircraft using an underway watercraft increases medical evacuation reach and flexibility in maritime environments. The selection of any one of…
Optimal Ground Station Selection for Low-Earth Orbiting Satellites
Duncan Eddy, Michelle Ho, Mykel J. Kochenderfer
This paper presents a solution to the problem of optimal ground station selection for low-Earth orbiting (LEO) space missions that enables mission operators to precisely design the…
Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approach
Zahra Shahrooei, Mykel J. Kochenderfer, Ali Baheri
Testing controllers in safety-critical systems is vital for ensuring their safety and preventing failures. In this paper, we address the falsification problem within learning-based…
Informative Input Design for Dynamic Mode Decomposition
Joshua Ott, Mykel J. Kochenderfer, Stephen Boyd
Efficiently estimating system dynamics from data is essential for minimizing data collection costs and improving model performance. This work addresses the challenge of designing f…
Watercraft as Overwater Ambulance Exchange Points to Enhance Aeromedical Evacuation
Mahdi Al-Husseini, Kyle H. Wray, Mykel J. Kochenderfer
Ambulance exchange points are preidentified sites where patients are transferred between evacuation platforms while en route to enhanced medical care. We propose a new capability f…
Probabilistic Parameter Estimators and Calibration Metrics for Pose Estimation from Image Features
Romeo Valentin, Sydney M. Katz, Joonghyun Lee +3
This paper addresses the challenge of probabilistic parameter estimation given measurement uncertainty in real-time. We provide a general formulation and apply this to pose estimat…
Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving
Bernard Lange, Masha Itkina, Jiachen Li +1
Environment prediction frameworks are critical for the safe navigation of autonomous vehicles (AVs) in dynamic settings. LiDAR-generated occupancy grid maps (L-OGMs) offer a robust…
Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments
Mansur Arief, Mike Timmerman, Jiachen Li +2
Training intelligent agents to navigate highly interactive environments presents significant challenges. While guided meta reinforcement learning (RL) approach that first trains a…
Open Problems in Technical AI Governance
Anka Reuel, Ben Bucknall, Stephen Casper +30
AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the barriers and uncertainties faced are at…
ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts
Amelia F. Hardy, Houjun Liu, Allie Griffith +3
Existing LLM red-teaming approaches prioritize high attack success rate, often resulting in high-perplexity prompts. This focus overlooks low-perplexity attacks that are more diffi…
Hierarchical Framework for Optimizing Wildfire Surveillance and Suppression using Human-Autonomous Teaming
Mahdi Al-Husseini, Kyle Wray, Mykel Kochenderfer
The integration of manned and unmanned aircraft can help improve wildfire response. Wildfire containment failures occur when resources available to first responders, who execute th…
Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems
Harrison Delecki, Marc R. Schlichting, Mansur Arief +3
Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Mon…
Distributed Online Planning for Min-Max Problems in Networked Markov Games
Alexandros E. Tzikas, Jinkyoo Park, Mykel J. Kochenderfer +1
Min-max problems are important in multi-agent sequential decision-making because they improve the performance of the worst-performing agent in the network. However, solving the mul…
SEEK: Semantic Reasoning for Object Goal Navigation in Real World Inspection Tasks
Muhammad Fadhil Ginting, Sung-Kyun Kim, David D. Fan +3
This paper addresses the problem of object-goal navigation in autonomous inspections in real-world environments. Object-goal navigation is crucial to enable effective inspections i…