Dual Control for Interactive Autonomous Merging with Model Predictive Diffusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929715361611776 |
|---|---|
| author | Knaup, Jacob D'sa, Jovin Chalaki, Behdad Mahjoub, Hossein Nourkhiz Moradi-Pari, Ehsan Tsiotras, Panagiotis |
| author_facet | Knaup, Jacob D'sa, Jovin Chalaki, Behdad Mahjoub, Hossein Nourkhiz Moradi-Pari, Ehsan Tsiotras, Panagiotis |
| contents | Interactive decision-making is essential in applications such as autonomous driving, where the agent must infer the behavior of nearby human drivers while planning in real-time. Traditional predict-then-act frameworks are often insufficient or inefficient because accurate inference of human behavior requires a continuous interaction rather than isolated prediction. To address this, we propose an active learning framework in which we rigorously derive predicted belief distributions. Additionally, we introduce a novel model-based diffusion solver tailored for online receding horizon control problems, demonstrated through a complex, non-convex highway merging scenario. Our approach extends previous high-fidelity dual control simulations to hardware experiments, which may be viewed at https://youtu.be/Q_JdZuopGL4, and verifies behavior inference in human-driven traffic scenarios, moving beyond idealized models. The results show improvements in adaptive planning under uncertainty, advancing the field of interactive decision-making for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dual Control for Interactive Autonomous Merging with Model Predictive Diffusion Knaup, Jacob D'sa, Jovin Chalaki, Behdad Mahjoub, Hossein Nourkhiz Moradi-Pari, Ehsan Tsiotras, Panagiotis Robotics Systems and Control Optimization and Control Interactive decision-making is essential in applications such as autonomous driving, where the agent must infer the behavior of nearby human drivers while planning in real-time. Traditional predict-then-act frameworks are often insufficient or inefficient because accurate inference of human behavior requires a continuous interaction rather than isolated prediction. To address this, we propose an active learning framework in which we rigorously derive predicted belief distributions. Additionally, we introduce a novel model-based diffusion solver tailored for online receding horizon control problems, demonstrated through a complex, non-convex highway merging scenario. Our approach extends previous high-fidelity dual control simulations to hardware experiments, which may be viewed at https://youtu.be/Q_JdZuopGL4, and verifies behavior inference in human-driven traffic scenarios, moving beyond idealized models. The results show improvements in adaptive planning under uncertainty, advancing the field of interactive decision-making for real-world applications. |
| title | Dual Control for Interactive Autonomous Merging with Model Predictive Diffusion |
| topic | Robotics Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2502.09918 |