Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mobarakeh, Niloufar Saeidi, Khamidehi, Behzad, Li, Chunlin, Mirkhani, Hamidreza, Arasteh, Fazel, Elmahgiubi, Mohammed, Zhang, Weize, Rezaee, Kasra, Poupart, Pascal
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915053225115648
author Mobarakeh, Niloufar Saeidi
Khamidehi, Behzad
Li, Chunlin
Mirkhani, Hamidreza
Arasteh, Fazel
Elmahgiubi, Mohammed
Zhang, Weize
Rezaee, Kasra
Poupart, Pascal
author_facet Mobarakeh, Niloufar Saeidi
Khamidehi, Behzad
Li, Chunlin
Mirkhani, Hamidreza
Arasteh, Fazel
Elmahgiubi, Mohammed
Zhang, Weize
Rezaee, Kasra
Poupart, Pascal
contents The primary goal of motion planning is to generate safe and efficient trajectories for vehicles. Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts. However, these models often lack interpretability and fail to provide clear justifications for their decisions. We propose a method that integrates constraint learning into imitation learning by extracting driving constraints from expert trajectories. Our approach utilizes vectorized scene embeddings that capture critical spatial and temporal features, enabling the model to identify and generalize constraints across various driving scenarios. We formulate the constraint learning problem using a maximum entropy model, which scores the motion planner's trajectories based on their similarity to the expert trajectory. By separating the scoring process into distinct reward and constraint streams, we improve both the interpretability of the planner's behavior and its attention to relevant scene components. Unlike existing constraint learning methods that rely on simulators and are typically embedded in reinforcement learning (RL) or inverse reinforcement learning (IRL) frameworks, our method operates without simulators, making it applicable to a wider range of datasets and real-world scenarios. Experimental results on the InD and TrafficJams datasets demonstrate that incorporating driving constraints enhances model interpretability and improves closed-loop performance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05717
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories
Mobarakeh, Niloufar Saeidi
Khamidehi, Behzad
Li, Chunlin
Mirkhani, Hamidreza
Arasteh, Fazel
Elmahgiubi, Mohammed
Zhang, Weize
Rezaee, Kasra
Poupart, Pascal
Robotics
Artificial Intelligence
Machine Learning
The primary goal of motion planning is to generate safe and efficient trajectories for vehicles. Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts. However, these models often lack interpretability and fail to provide clear justifications for their decisions. We propose a method that integrates constraint learning into imitation learning by extracting driving constraints from expert trajectories. Our approach utilizes vectorized scene embeddings that capture critical spatial and temporal features, enabling the model to identify and generalize constraints across various driving scenarios. We formulate the constraint learning problem using a maximum entropy model, which scores the motion planner's trajectories based on their similarity to the expert trajectory. By separating the scoring process into distinct reward and constraint streams, we improve both the interpretability of the planner's behavior and its attention to relevant scene components. Unlike existing constraint learning methods that rely on simulators and are typically embedded in reinforcement learning (RL) or inverse reinforcement learning (IRL) frameworks, our method operates without simulators, making it applicable to a wider range of datasets and real-world scenarios. Experimental results on the InD and TrafficJams datasets demonstrate that incorporating driving constraints enhances model interpretability and improves closed-loop performance.
title Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.05717