講座名稱：Distributed Autonomous Separation Assurance with Deep Multi-Agent Reinforcement Learning

講座人：衛(wèi)鵬 助理教授

講座時間：7月2日10:00

講座地點：騰訊會議直播 (會議ID：611 247 716 鏈接：https://meeting.tencent.com/s/73UIbiJrYWzU ）

講座人介紹：

衛(wèi)鵬，2007年獲得清華大學(xué)學(xué)士學(xué)位，2013年獲得美國普渡大學(xué)博士學(xué)位。目前為喬治華盛頓大學(xué)機械與航空航天工程系助理教授，喬治華盛頓大學(xué)的智能航空航天系統(tǒng)實驗室 (IASL)負(fù)責(zé)人。研究領(lǐng)域為控制、優(yōu)化、機器學(xué)習(xí)和人工智能的方面的綜合應(yīng)用，主要工作為航空、航空和空中機器人開發(fā)了提供了自主和決策支持工具。他目前的研究重點是復(fù)雜和不確定的動態(tài)環(huán)境中系統(tǒng)決策的安全性、有效性效率和可擴(kuò)展性。此外為AIAA Journal of Aerospace Information Systems 的副主編。

講座內(nèi)容：

A novel deep multi-agent reinforcement learning framework is proposed to resolve conflicts among a variable number of aircraft in a high-density, stochastic, and dynamic sector. Currently the sector capacity is constrained by human air traffic controller's cognitive limitation. We investigate the feasibility of a new concept (autonomous separation assurance) and a new approach to push the sector capacity above human cognitive limitation. We propose the concept of using distributed vehicle autonomy to ensure separation, instead of a centralized sector air traffic controller. Our proposed framework utilizes Proximal Policy Optimization (PPO) that we modify to incorporate an attention network. This allows the agents to have access to variable aircraft information in the sector in a scalable, efficient approach to achieve high traffic throughput under uncertainty. Agents are trained using a centralized learning, decentralized execution scheme where one neural network is learned and shared by all agents. The proposed framework is validated on three challenging case studies in the BlueSky air traffic control environment. Numerical results show the proposed framework significantly reduces offline training time, increases performance, and results in a more efficient policy.

主辦單位：機電工程學(xué)院