Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty

• URL: http://arxiv.org/abs/2605.20255v2
• Date: Mon, 25 May 2026 19:49:33 GMT
• Title: Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
• Abstract summary: We co-train an SDC and 12 pedestrians using Multi-Agent Proximal Policy Optimization (MAPPO)<n>In 500-episode evaluations, the co-trained SDC reached 78% of goals with a 14% collision rate, versus 35%/33% for the best rule-based baseline.<n>Jaywalking was 13% of crossing events but 62% of collisions, and co-training reduced collisions by 30% relative to single-agent RL.
• Score: 3.682030314397244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simulation-based testing of self-driving cars (SDCs) typically relies on scripted pedestrian models that do not capture the heterogeneity and uncertainty of real crossing behavior, limiting the realism of safety assessments, especially for jaywalking, which is governed by latent personality traits the vehicle cannot observe. We hypothesize that jointly training pedestrians and the SDC with multi-agent reinforcement learning (MARL) yields more realistic interaction scenarios than training against fixed pedestrian policies, and that the behavior gap between predictable and unpredictable crossings can be measured directly from trajectories. We co-train an SDC and 12 pedestrians using Multi-Agent Proximal Policy Optimization (MAPPO): pedestrian locomotion follows scripted Dijkstra pathfinding while an RL policy controls high-level go/wait decisions, and jaywalking probability depends on a per-pedestrian trait sampled at episode start and hidden from the SDC. In 500-episode evaluations, the co-trained SDC reached 78% of goals with a 14% collision rate, versus 35%/33% for the best rule-based baseline. A speed differential metric shows the SDC traveled 2.65 m/s faster near jaywalkers than near crosswalk users at close range (0-3 m), indicating jaywalking encounters were not anticipated. Jaywalking was 13% of crossing events but 62% of collisions, and co-training reduced collisions by 30% relative to single-agent RL as pedestrians learned to wait when the SDC approached at speed.

Related papers

• Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles [5.343135467323389]
  Large Language Model (LLM)-based decision-making framework for pedestrian-aware behavioral planning.<n>System converts structured scene observations into natural-language reasoning prompts, enabling the LLM to infer pedestrian intent, anticipate risk, and generate cautious tactical driving decisions.<n>We evaluate the framework in SUMO across multiple pedestrian-interaction scenarios, including unexpected jaywalking, turn-back crossing, hesitation, and bidirectional crossing.
  arXiv  Detail & Related papers  (2026-05-16T07:41:42Z)
• Autonomous Vehicle Collision Avoidance With Racing Parameterized Deep Reinforcement Learning [73.88859384645264]
  Road traffic accidents are a leading cause of fatalities worldwide.<n>In the US, human error causes 94% of crashes, resulting in over 7,000 pedestrian fatalities and $500 billion in costs annually.<n>This paper parameterizes a Deep Reinforcement Learning (DRL) collision avoidance policy out-of-Distribution.<n>Two policies are evaluated, a default uni-direction and a reversed heading variant that navigates in the opposite direction to other cars.
  arXiv  Detail & Related papers  (2026-04-17T21:11:39Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space [3.487370856323828]
  This work introduces an integrated prediction and planning approach that incorporates the uncertainties of predicted pedestrian states in the training of a model-free DRL algorithm. A novel reward function encourages the AV to respect pedestrians' personal space, decrease speed during close approaches, and minimize the collision probability with their predicted paths. Results show a 40% decrease in collision rate and a 15% increase in minimum distance to pedestrians compared to the state of the art model that does not account for prediction uncertainty.
  arXiv  Detail & Related papers  (2024-05-22T20:09:21Z)
• iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning [57.24340061741223]
  We introduce a distributed multi-agent reinforcement learning (MARL) algorithm that can predict trajectories and intents in dense and heterogeneous traffic scenarios. Our approach for intent-aware planning, iPLAN, allows agents to infer nearby drivers' intents solely from their local observations.
  arXiv  Detail & Related papers  (2023-06-09T20:12:02Z)
• Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories [88.08381083207449]
  We show the prevalence of emphgeneralization failure on controllable states from stranger agents. We propose a novel method called Self-Trajectory Augmentation (STA), which will reset the environment to the agent's old states according to the Q function during training.
  arXiv  Detail & Related papers  (2023-04-26T10:12:12Z)
• Cross or Wait? Predicting Pedestrian Interaction Outcomes at Unsignalized Crossings [12.800489342833275]
  We use machine learning to predict pedestrian crossing behavior including pedestrian crossing decision, crossing initiation time (CIT), and crossing duration (CD) when interacting with vehicles at unsignalized crossings. Compared with the logistic regression baseline model, our proposed neural network model improves the prediction accuracy and F1 score by 4.46% and 3.23%, respectively. Our model also reduces the root mean squared error (RMSE) for CIT and CD by 21.56% and 30.14% compared with the linear regression model.
  arXiv  Detail & Related papers  (2023-04-17T13:20:04Z)
• Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion [87.77727495366702]
  We introduce the new task of pedestrian stop and go forecasting. Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic. We build it from several existing datasets annotated with pedestrians' walking motions, in order to have various scenarios and behaviors.
  arXiv  Detail & Related papers  (2022-03-04T18:39:31Z)
• Modeling Interactions of Autonomous Vehicles and Pedestrians with Deep Multi-Agent Reinforcement Learning for Collision Avoidance [20.542143534865154]
  In this work, we model the corresponding interaction sequence as a Markov decision process (MDP) that is solved by deep reinforcement learning (DRL) algorithms. The presented PCAM system with different levels of intelligent pedestrian behavior is benchmarked according to the agents' collision rate and the resulting traffic flow efficiency. The results show that the AV is able to completely mitigate collisions under the majority of the investigated conditions.
  arXiv  Detail & Related papers  (2021-09-30T17:06:39Z)
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles [103.87351701138554]
  In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes. We introduce a Multi-Task Learning (MTL) model relying on a composite field framework, which achieves both goals in an efficient way. We show competitive detection and attribute recognition results, as well as a more stable MTL training.
  arXiv  Detail & Related papers  (2020-12-04T15:10:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.