홈 › Papers

Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehicles

2018-12-14 · Kathy Jang, Eugene Vinitsky, Behdad Chalaki, Ben Remer, Logan Beaver, Andreas Malikopoulos, Alexandre Bayen

Using deep reinforcement learning, we train control policies for autonomous vehicles leading a platoon of vehicles onto a roundabout. Using Flow, a library for deep reinforcement learning in micro-simulators, we train two policies, one policy with noise injected into the state and action space and one without any injected noise. In simulation, the autonomous vehicle learns an emergent metering behavior for both policies in which it slows to allow for smoother merging. We then directly transfer this policy without any tuning to the University of Delaware Scaled Smart City (UDSSC), a 1:25 scale testbed for connected and automated vehicles. We characterize the performance of both policies on the scaled city. We show that the noise-free policy winds up crashing and only occasionally metering. However, the noise-injected policy consistently performs the metering behavior and remains collision-free, suggesting that the noise helps with the zero-shot policy transfer. Additionally, the transferred, noise-injected policy leads to a 5% reduction of average travel time and a reduction of 22% in maximum travel time in the UDSSC. Videos of the controllers can be found at https://sites.google.com/view/iccps-policy-transfer.

📄 PDF Abstract BibTeX arXiv:1812.06120

Code (1)

flow-project/flow 공식 구현

Tasks

Autonomous VehiclesDeep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem

2025-10-09 · Francisco Pascoa, Ian Lalonde, Alexandre Girard arxiv

Reinforcement learning (RL) policies often fail to generalize to new robots, tasks, or environments with different physical parameters, a challenge that limits their real-world applicability. This paper presents a simple…

Reinforcement Learning

SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds

2026-04-09 · Yunsong Zhou, Hangxu Liu, Xuekun Jiang, Xing Shen 외 arxiv

Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in ways that far exceed the variability of rigids. Although simulation pr…

Generative Simulation for Policy Learning in Physical Human-Robot Interaction

2026-04-09 · Junxiang Wang, Xinwen Xu, Tiancheng Wu, Julian Millan 외 arxiv

Developing autonomous physical human-robot interaction (pHRI) systems is limited by the scarcity of large-scale training data to learn robust robot behaviors for real-world applications. In this paper, we introduce a zer…

Point Clouds

Point Bridge: 3D Representations for Cross Domain Policy Learning

2026-01-22 · Siddhant Haldar, Lars Johannsmeier, Lerrel Pinto, Abhishek Gupta 외 arxiv

Robot foundation models are beginning to deliver on the promise of generalist robotic agents, yet progress remains constrained by the scarcity of large-scale real-world manipulation datasets. Simulation and synthetic dat…

Synthetic Data Generation

Efficient Real-World Autonomous Racing via Attenuated Residual Policy Optimization

2026-03-13 · Raphael Trumpp, Denis Hoornaert, Mirco Theile, Marco Caccamo arxiv

Residual policy learning (RPL), in which a learned policy refines a static base policy using deep reinforcement learning (DRL), has shown strong performance across various robotic applications. Its effectiveness is parti…