# Using High-Level Patterns to Estimate How Humans Predict a Robot will Behave

arXiv: https://arxiv.org/abs/2409.13533 · HTML: https://mlsanity.com/paper/2409.13533/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 19 of 19)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps](https://mlsanity.com/paper/1910.03088/) (2019)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [Learning Latent Representations to Influence Multi-Agent Interaction](https://mlsanity.com/paper/2011.06619/) (2020)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization](https://mlsanity.com/paper/2205.07547/) (2022)
- [Agent Modelling under Partial Observability for Deep Reinforcement Learning](https://mlsanity.com/paper/2006.09447/) (2020)
- [Shared Autonomy via Hindsight Optimization for Teleoperation and Teaming](https://mlsanity.com/paper/1706.00155/) (2017)
- [Shared Autonomy with Learned Latent Actions](https://mlsanity.com/paper/2005.03210/) (2020)
- [Learning Representations that Enable Generalization in Assistive Tasks](https://mlsanity.com/paper/2212.03175/) (2022)
- [I Know What You Meant: Learning Human Objectives by (Under)estimating Their Choice Set](https://mlsanity.com/paper/2011.06118/) (2020)
- [Emergence of Theory of Mind Collaboration in Multiagent Systems](https://mlsanity.com/paper/2110.00121/) (2021)
- [Improving Multi-Agent Cooperation using Theory of Mind](https://mlsanity.com/paper/2007.15703/) (2020)
- [Learning Latent Representations to Co-Adapt to Humans](https://mlsanity.com/paper/2212.09586/) (2022)
- [Building Second-Order Mental Models for Human-Robot Interaction](https://mlsanity.com/paper/1909.06508/) (2019)
- [Epistemic Prediction and Planning with Implicit Coordination for Multi-Robot Teams in Communication Restricted Environments](https://mlsanity.com/paper/2302.10393/) (2023)

## Abstract (arXiv)

Humans interacting with robots often form predictions of what the robot will do next. For instance, based on the recent behavior of an autonomous car, a nearby human driver might predict that the car is going to remain in the same lane. It is important for the robot to understand the human's prediction for safe and seamless interaction: e.g., if the autonomous car knows the human thinks it is not merging -- but the autonomous car actually intends to merge -- then the car can adjust its behavior to prevent an accident. Prior works typically assume that humans make precise predictions of robot behavior. However, recent research on human-human prediction suggests the opposite: humans tend to approximate other agents by predicting their high-level behaviors. We apply this finding to develop a second-order theory of mind approach that enables robots to estimate how humans predict they will behave. To extract these high-level predictions directly from data, we embed the recent human and robot trajectories into a discrete latent space. Each element of this latent space captures a different type of behavior (e.g., merging in front of the human, remaining in the same lane) and decodes into a vector field across the state space that is consistent with the underlying behavior type. We hypothesize that our resulting high-level and course predictions of robot behavior will correspond to actual human predictions. We provide initial evidence in support of this hypothesis through proof-of-concept simulations, testing our method's predictions against those of real users, and experiments on a real-world interactive driving dataset.