Assistant professor at University of Utah. Researching robot learning, reward/imitation learning, HRI, and AI safety.
Joined April 2019
- Tweets197
- Following123
- Followers803
- Likes274
Pinned Tweet
Imitation learning is a popular approach to train robots, but how robust are the learned policies? I'm excited about our new paper led by @KalraAkansha that performs the first comparison of policy vulnerabilities across a range of popular algorithms amd attacks.
Robot policies are getting remarkably capable—but are they robust enough to deploy?
We are moving towards an increasing deployment of pre-trained AI models with publicly released parameters and with no downstream retraining required.
But how vulnerable are these pre-trained models to adversarial attacks?
Our new work explores White-box, Grey-box and Black-box attacks across a range of both classic and recently proposed Imitation Learning(IL) algorithms, including Vanilla Behavior Cloning (Vanilla BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and Vector-Quantized Behavior Transformer (VQ-BET).
1/3
I was recently selected to receive the University of Utah's Responsible AI Faculty Fellowship! As part of this fellowship I will be developing the next generation of assistive robots and studying human and robot co-adaptation in hospitals and homes: price.utah.edu/2026/10/14/fo…
I'm really excited about the potential to use very limited local sensing to enable members of a swarm to know what the entire collective is doing and enable swarm-level behavior changes and coordination!
Excited to showcase our paper “ SyncSBC: Decentralized Swarm Behavior Prediction for Synchronized Autonomous Control” at #IROS2026!!
🧵 How does a robot in a swarm know what the collective swarm is doing?
Paper: lnkd.in/gmt2CNiJ
Website: lnkd.in/gwvUEFVp
Super excited to work with an amazing group of people on developing the science of human-robot co-adaptation!
I'm incredibly excited to lead the new NSF Center for Human and Robot Co-Adaptation!
It is one of three new $30M, 5yr Centers launched under the @NSF STC program, and is led by @UTAustin , with partners @IUBloomington , @MIT , @TuftsUniversity , @UUtah , and @Yale
Shared autonomy is a great way to combine the strengths of a human and a robot. But current systems are often opaque as to what the robot thinks the human wants. I'm excited about our new IROS paper that studies how to provide transparency and boost trust for better HRI!
Really excited about our new RLC paper that extends machine teaching for reward functions to multiple teaching modalities enabling generalization to new environments!
How do you teach an agent what you want — so it still holds when the environment changes?
Our paper, Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning, is at RLC 2026!
w/ @QianLin44, Chang Zong Wu, @daniel_s_brown
arxiv.org/abs/2607.08647
🧵1/7
Our paper "A Multi-Layer Sim-to-Real Framework for Gaze-Driven Assistive Neck Exoskeletons" is being presented this week at ICRA 2026!
arxiv.org/abs/2603.06779
🧵1/8
We find that our two of our three data-driven gaze controllers are competitive or superior to prior state-of-the-art. Interestingly, there is no single overall "best" controller. We found three non-dominated controllers and which one is best depends on the individual user.
🧵7/8
This motivates per-user adaptation and personalization, an exciting area of future work! This has been a really fun collaboration within the @URoboticsCenter. Kudos to co-Authors: Colin Rubow, Eric Brewer, Ian Bales, and Haohan Zhang!
arxiv.org/abs/2603.06779
🧵8/8
Excited to share our new paper on implicit safety alignment from crowd feedback that was accepted at ICML! We learn shared safety constraints from crowd feedback and show this can help alleviate reward mispecification. Kudos to @QianLin44 for this really fun piece of work!
What if your task reward is imperfect — especially when it misses safety-related objectives? Maybe crowd preferences can help.
Excited to share our paper, Implicit Safety Alignment from Crowd Preferences, accepted to ICML 2026! Grateful to @daniel_s_brown for his guidance and support on this work.
Paper: arxiv.org/abs/2605.21822
🧵1/7
Super excited about our lab's new paper led by @zifan_w: "Understanding the Effects of Neuron Dominance in Deep Reinforcement Learning", that has been published in Transactions on Machine Learning Research (TMLR)!
openreview.net/forum?id=VNV1…
1/N
Excited to share that our paper, "Understanding the Effects of Neuron Dominance in Deep Reinforcement Learning", has been published in Transactions on Machine Learning Research!
Full paper: openreview.net/forum?id=VNV1…
Work with Qian Lin, Blake Lawlor, Haijun Zhao, and Daniel Brown.
4. We provide a novel theoretical explanation for why classification losses like HL-Gauss resist representation collapse: unlike MSE regression, the softmax nonlinearity prevents gradients from vanishing even when the representation collapses to zero.
6/N
This work offers a new mechanistic lens for understanding why normalization, resets, and classification-based value learning work in deep RL — and provides practical guidance for choosing among them depending on reward sparsity.
Full paper: openreview.net/forum?id=VNV1…
7/N