IANN-MPPI: Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral Approach for Autonomous Driving
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909690453032960 |
|---|---|
| author | Ryu, Kanghyun Sung, Minjun Gupta, Piyush D'sa, Jovin Tariq, Faizan M. Isele, David Bae, Sangjae |
| author_facet | Ryu, Kanghyun Sung, Minjun Gupta, Piyush D'sa, Jovin Tariq, Faizan M. Isele, David Bae, Sangjae |
| contents | Motion planning for autonomous vehicles (AVs) in dense traffic is challenging, often leading to overly conservative behavior and unmet planning objectives. This challenge stems from the AVs' limited ability to anticipate and respond to the interactive behavior of surrounding agents. Traditional decoupled prediction and planning pipelines rely on non-interactive predictions that overlook the fact that agents often adapt their behavior in response to the AV's actions. To address this, we propose Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral (IANN-MPPI) control, which enables interactive trajectory planning by predicting how surrounding agents may react to each control sequence sampled by MPPI. To improve performance in structured lane environments, we introduce a spline-based prior for the MPPI sampling distribution, enabling efficient lane-changing behavior. We evaluate IANN-MPPI in a dense traffic merging scenario, demonstrating its ability to perform efficient merging maneuvers. Our project website is available at https://sites.google.com/berkeley.edu/iann-mppi |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11940 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IANN-MPPI: Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral Approach for Autonomous Driving Ryu, Kanghyun Sung, Minjun Gupta, Piyush D'sa, Jovin Tariq, Faizan M. Isele, David Bae, Sangjae Robotics Systems and Control Motion planning for autonomous vehicles (AVs) in dense traffic is challenging, often leading to overly conservative behavior and unmet planning objectives. This challenge stems from the AVs' limited ability to anticipate and respond to the interactive behavior of surrounding agents. Traditional decoupled prediction and planning pipelines rely on non-interactive predictions that overlook the fact that agents often adapt their behavior in response to the AV's actions. To address this, we propose Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral (IANN-MPPI) control, which enables interactive trajectory planning by predicting how surrounding agents may react to each control sequence sampled by MPPI. To improve performance in structured lane environments, we introduce a spline-based prior for the MPPI sampling distribution, enabling efficient lane-changing behavior. We evaluate IANN-MPPI in a dense traffic merging scenario, demonstrating its ability to perform efficient merging maneuvers. Our project website is available at https://sites.google.com/berkeley.edu/iann-mppi |
| title | IANN-MPPI: Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral Approach for Autonomous Driving |
| topic | Robotics Systems and Control |
| url | https://arxiv.org/abs/2507.11940 |