MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
This research presents MAPLE, a novel framework designed to improve the robustness of vision-language-action (VLA) models in end-to-end autonomous driving.
The paper introduces MAPLE, a framework for closed-loop training of vision-language-action models in autonomous driving using latent multi-agent play without external simulators, achieving state-of-the-art results on Bench2Drive.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S5
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
l fidelity to the real-world. MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
Open source S5
arXiv:2605.14201v3 Announce Type: replace Abstract: Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing closed-loop supervision approaches lack scalability and fail to completely model a reactive environment. We propose MAPLE, a novel framework for reacti
Open source S2
ve, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model. The ego vehicle and nearby traffic agents are independently controlled over multi-step horizons, while being reactive to other agents in the scene, enabling closed-loop training. MAPLE consists of two training stages: (1) supervised fine-tuning on the latent rollouts based on ground-truth trajectories, followed by (2) reinforc
Open source S3
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
Open source S1
Source：arXiv Robotics — research abstracts · arxiv.org