6 papers
RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
Ehsan Ahmadi, Hunter Schofield, Behzad Khamidehi +5
Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common i…
Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
Fazel Arasteh, Arian Haghparast, Manos Papagelis
Traffic congestion in urban road networks leads to longer trip times and higher emissions, especially during peak periods. While the Shortest Path First (SPF) algorithm is optimal…
CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving
Hamidreza Mirkhani, Behzad Khamidehi, Ehsan Ahmadi +6
In this paper, we introduce Context-Aware Priority Sampling (CAPS), a novel method designed to enhance data efficiency in learning-based autonomous driving systems. CAPS addresses…
Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories
Niloufar Saeidi Mobarakeh, Behzad Khamidehi, Chunlin Li +6
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…
Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning
Fazel Arasteh, Mohammed Elmahgiubi, Behzad Khamidehi +4
The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their sur…
Analysis of a Modular Autonomous Driving Architecture: The Top Submission to CARLA Leaderboard 2.0 Challenge
Weize Zhang, Mohammed Elmahgiubi, Kasra Rezaee +8
In this paper we present the architecture of the Kyber-E2E submission to the map track of CARLA Leaderboard 2.0 Autonomous Driving (AD) challenge 2023, which achieved first place.…