# Analyzing Human Models that Adapt Online

arXiv: https://arxiv.org/abs/2103.05746 · HTML: https://mlsanity.com/paper/2103.05746/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 9 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [Reachability Analysis of Deep Neural Networks with Provable Guarantees](https://mlsanity.com/paper/1805.02242/) (2018)
- [Understanding the Acceleration Phenomenon via High-Resolution Differential Equations](https://mlsanity.com/paper/1810.08907/) (2018)
- [Shared Autonomy via Hindsight Optimization](https://mlsanity.com/paper/1503.07619/) (2015)
- [Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraints](https://mlsanity.com/paper/1410.6445/) (2014)
- [A Lyapunov Analysis of Momentum Methods in Optimization](https://mlsanity.com/paper/1611.02635/) (2016)
- [Probabilistically Safe Robot Planning with Confidence-Based Human Predictions](https://mlsanity.com/paper/1806.00109/) (2018)
- [Learning under Misspecified Objective Spaces](https://mlsanity.com/paper/1810.05157/) (2018)
- [Nesterov's method with decreasing learning rate leads to accelerated stochastic gradient descent](https://mlsanity.com/paper/1908.07861/) (2019)
- [A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance](https://mlsanity.com/paper/1811.05929/) (2018)
- [A Hamilton-Jacobi Reachability-Based Framework for Predicting and Analyzing Human Motion for Safe Planning](https://mlsanity.com/paper/1910.13369/) (2019)
- [Control Theory Meets POMDPs: A Hybrid Systems Approach](https://mlsanity.com/paper/1905.08095/) (2019)

## Built on by (most cited first, 8 of 8)

- [Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis](https://mlsanity.com/paper/2502.00935/) (2025)
- [The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review](https://mlsanity.com/paper/2308.05731/) (2023)
- [Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction](https://mlsanity.com/paper/2210.05976/) (2022)
- [Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models](https://mlsanity.com/paper/2104.10558/) (2021)
- [Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach](https://mlsanity.com/paper/2302.00171/) (2023)
- [Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy](https://mlsanity.com/paper/2309.01267/) (2023)
- [Online Residual Learning from Offline Experts for Pedestrian Tracking](https://mlsanity.com/paper/2409.04069/) (2024)
- [Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics](https://mlsanity.com/paper/2606.02562/) (2026)

## Abstract (arXiv)

Predictive human models often need to adapt their parameters online from human data. This raises previously ignored safety-related questions for robots relying on these models such as what the model could learn online and how quickly could it learn it. For instance, when will the robot have a confident estimate in a nearby human's goal? Or, what parameter initializations guarantee that the robot can learn the human's preferences in a finite number of observations? To answer such analysis questions, our key idea is to model the robot's learning algorithm as a dynamical system where the state is the current model parameter estimate and the control is the human data the robot observes. This enables us to leverage tools from reachability analysis and optimal control to compute the set of hypotheses the robot could learn in finite time, as well as the worst and best-case time it takes to learn them. We demonstrate the utility of our analysis tool in four human-robot domains, including autonomous driving and indoor navigation.