Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.19292 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913369072599040 |
|---|---|
| author | Khan, Hamzah I. Thorpe, Adam J. Fridovich-Keil, David |
| author_facet | Khan, Hamzah I. Thorpe, Adam J. Fridovich-Keil, David |
| contents | Autonomous agents operating around human actors must consider how their behaviors might affect those humans, even when not directly interacting with them. To this end, it is often beneficial to be predictable and appear naturalistic. Existing methods to address this problem use human actor intent modeling or imitation learning techniques, but these approaches rarely capture all possible motivations for human behavior or require significant amounts of data. In contrast, we propose a technique for modeling naturalistic behavior as a set of convex hulls computed over a relatively small dataset of human behavior. Given this set, we design an optimization-based filter which projects arbitrary trajectories into it to make them more naturalistic for autonomous agents to execute while also satisfying dynamics constraints. We demonstrate our methods on real-world human driving data from the inD intersection dataset (Bock et al., 2020). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19292 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Act Natural! Projecting Autonomous System Trajectories Into Naturalistic Behavior Sets Khan, Hamzah I. Thorpe, Adam J. Fridovich-Keil, David Multiagent Systems Autonomous agents operating around human actors must consider how their behaviors might affect those humans, even when not directly interacting with them. To this end, it is often beneficial to be predictable and appear naturalistic. Existing methods to address this problem use human actor intent modeling or imitation learning techniques, but these approaches rarely capture all possible motivations for human behavior or require significant amounts of data. In contrast, we propose a technique for modeling naturalistic behavior as a set of convex hulls computed over a relatively small dataset of human behavior. Given this set, we design an optimization-based filter which projects arbitrary trajectories into it to make them more naturalistic for autonomous agents to execute while also satisfying dynamics constraints. We demonstrate our methods on real-world human driving data from the inD intersection dataset (Bock et al., 2020). |
| title | Act Natural! Projecting Autonomous System Trajectories Into Naturalistic Behavior Sets |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2405.19292 |