Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

Navigate
  • About
  • Events
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
  • Research

    • Research
    • Fellowship Programs
    • Grants
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs
peopleFaculty,Senior Fellow

Mykel Kochenderfer

Associate Professor of Aeronautics and Astronautics, Stanford University | Senior Fellow, Stanford HAI | Director, Stanford Intelligent Systems Laboratory (SISL)

Topics
Robotics
Automation
External Bio

Mykel Kochenderfer is an Associate Professor of Aeronautics and Astronautics at Stanford University. He is the director of the Stanford Intelligent Systems Laboratory (SISL), conducting research on advanced algorithms and analytical methods for the design of robust decision making systems. Of particular interest are systems for air traffic control, unmanned aircraft, and automated driving where decisions must be made in uncertain, dynamic environments while maintaining safety and efficiency. Research at SISL focuses on efficient computational methods for deriving optimal decision strategies from high-dimensional, probabilistic problem representations. Prior to joining the faculty in 2013, he was at MIT Lincoln Laboratory where he worked on aircraft collision avoidance, leading to the creation of the ACAS X international standard for manned and unmanned aircraft. Kochenderfer is a co-director of the Center for AI Safety. He is editor-in-chief of the Journal of Artificial Intelligence Research and associate editor of the Journal of Aerospace Information Systems. He is an author of the textbooks Decision Making under Uncertainty: Theory and Application (MIT Press, 2015), Algorithms for Optimization (MIT Press, 2019), and Algorithms for Decision Making (MIT Press, 2022).

Share
Link copied to clipboard!

Latest Related to Mykel Kochenderfer

Research
Your browser does not support the video tag.

BetaZero: Belief-State Planning for Long-Horizon POMDPs Using Learned Approximations

Anthony Corso, Jef Caers, Robert J. Moss, Mykel Kochenderfer
AutomationRoboticsJul 31

Real-world planning problems, including autonomous driving and sustainable energy applications like carbon storage and resource exploration, have recently been modeled as partially observable Markov decision processes (POMDPs) and solved using approximate methods. To solve high-dimensional POMDPs in practice, state- of-the-art methods use online planning with problem-specific heuristics to reduce planning horizons and make the problems tractable. Algorithms that learn approximations to replace heuristics have recently found success in large-scale fully observable domains. The key insight is the combination of online Monte Carlo tree search with offline neural network approximations of the optimal policy and value function. In this work, we bring this insight to partially observable domains and propose BetaZero, a belief-state planning algorithm for high-dimensional POMDPs. BetaZero learns offline approximations that replace heuristics to enable online decision making in long-horizon problems. We address several challenges inherent in large-scale partially observable domains; namely challenges of transitioning in stochastic environments, prioritizing action branching with a limited search bud- get, and representing beliefs as input to the network. To formalize the use of all limited search information, we train against a novel Q-weighted visit counts policy. We test BetaZero on various well-established POMDP benchmarks found in the literature and a real-world problem of critical mineral exploration. Experiments show that BetaZero outperforms state-of-the-art POMDP solvers on a variety of tasks.1

policy brief
What Makes a Good AI Benchmark

What Makes a Good AI Benchmark?

Malcolm Hardy, Amelia Hardy, Chandler Smith, Max Lamparth, Anka Reuel, Mykel Kochenderfer
Foundation ModelsPrivacy, Safety, SecurityDec 11

This brief presents a novel assessment framework for evaluating the quality of AI benchmarks and scores 24 benchmarks against the framework.

Research
Your browser does not support the video tag.

Finding Monosemantic Subspaces and Human-Compatible Interpretations in Vision Transformers through Sparse Coding

Romeo Valentin, Summeet Singh, Vikas Sindhwan, Vincent Vanhoucke, Mykel Kochenderfer
Computer VisionJan 01

We present a new method of deconstructing class activation tokens of vision transformers into a new, overcomplete basis, where each basis vector is “monosemantic” and affiliated with a single, human-compatible conceptual description. We achieve this through the use of a highly optimized and customized version of the K-SVD algorithm, which we call Double-Batch K-SVD (DBK-SVD). We demonstrate the efficacy of our approach on the sbucaptions dataset, using CLIP embeddings and comparing our results to a Sparse Autoencoder (SAE) baseline. Our method significantly outperforms SAE in terms of reconstruction loss, recovering approximately 2/3 of the original signal compared to 1/6 for SAE. We introduce novel metrics for evaluating explanation faithfulness and specificity, showing that DBK-SVD produces more diverse and specific concept descriptions. We therefore show empirically for the first time that disentangling of concepts arising in Vision Transformers is possible, a statement that has previously been questioned when applying an additional sparsity constraint. Our research opens new avenues for model interpretability, failure mitigation, and downstream task domain transfer in vision transformer models. An interactive demo showcasing our results can be found at https://disentangling-sbucaptions.xyz, and we make our DBK-SVD implementation openly available at https://github.com/RomeoV/KSVD.jl.