Get Started
Home
Topics
Search
Library
Research questionHow can low-cost platforms enable reproducible testing of end-to-end autonomous-driving policies across simulation and physical vehicles?Researchers need to compare autonomous-driving policies across simulated and physical runs, but inexpensive setups that make those experiments reproducible are scarce.
AI
Computer Vision
Evaluation & Benchmarks
Machine Learning
Robotics
Technology
Latest papersRecent research connected to this question, newest first.A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann VehicleThe evidence concerns an open platform combining a physical miniature Ackermann vehicle, a printed urban track, data-collection and trajectory-registration tools, and a Webots digital twin. It supports a camera-and-command-conditioned policy that outputs steering and speed, with closed-loop evaluation in simulation and on the vehicle; reported evidence includes track following, camera-field-of-view effects, and synthetic-data sim-to-real experiments.research paper · Sep 3, 2026
Related questions
How can world-model reinforcement learning produce reliable long-horizon driving policies amid interactive traffic and diverse driving styles?How can autonomous-driving planners be stress-tested in realistic closed-loop scenarios that expose failures missed by nominal benchmarks?How can vehicle-infrastructure cooperative driving be evaluated for error accumulation under occlusion without costly full simulation?How can safety assessors scale credibility judgments for virtual-testing toolchains across automated-driving decisions of differing criticality?