Attention-Based Policy Distillation for UAV Simultaneous Target Tracking and Obstacle Avoidance

避碰 计算机科学 强化学习 避障 障碍物 一般化 任务(项目管理) 人工智能 光学(聚焦) 跟踪(教育) 碰撞 机器人 移动机器人 工程类 计算机安全 数学 物理 光学 数学分析 法学 系统工程 教育学 政治学 心理学
作者
Lele Xu,Teng Wang,Jiawei Wang,Jian Liu,Changyin Sun
出处
期刊:IEEE transactions on intelligent vehicles [Institute of Electrical and Electronics Engineers]
卷期号:9 (2): 3768-3781 被引量:2
标识
DOI:10.1109/tiv.2023.3342174
摘要

Nowadays, deep reinforcement learning (DRL) has made remarkable achievements in the research of unmanned aerial vehicle (UAV) applications. However, much of the current research on UAVs focuses on a single task, which limits its applicability in many scenarios. Therefore, we have conducted research on UAV target tracking and obstacle avoidance tasks. The DRL-based solutions integrate the objectives of multi-tasks into a common reward function making the training unstable and difficult to converge, resulting in the loss of objectives or collisions. To that end, we propose a novel target following and obstacle avoidance solution based on policy distillation of the task attention mechanism. First, we train the two tasks of UAV target following and UAV obstacle avoidance respectively. Both networks are trained using Dueling Double Deep Q Network to learn the corresponding policy in an end-to-end manner. Then we extract the two policies that have been trained separately into a memory buffer. Meanwhile, we can perceive the collision risk through the state of the current environment of the UAV to assign the weights of the two tasks in the attention mechanism. Therefore, our method can adaptively focus on the corresponding tasks according to the current state. We conducted simulation experiments using the Virtual Robot Experimentation Platform. Our study presents compelling experimental findings: (1) Our novel approach outperforms state-of-the-art methods by achieving superior tracking accuracy and extended tracking durations across diverse environments, all while mitigating collision incidents. (2) The distilled policy we have developed exhibits robust generalization capabilities when applied to previously unencountered environments.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
陈12完成签到 ,获得积分10
刚刚
washy完成签到,获得积分10
刚刚
2秒前
小白杨完成签到,获得积分10
2秒前
4秒前
Jasper应助去码头整点海鸥采纳,获得10
4秒前
滴滴滴完成签到,获得积分20
5秒前
5秒前
无花果应助Sg采纳,获得10
5秒前
ziller完成签到,获得积分10
6秒前
7秒前
丰富赛凤发布了新的文献求助10
7秒前
乐观鱼发布了新的文献求助10
7秒前
8秒前
jevon应助sfxnxgu采纳,获得10
8秒前
9秒前
鲤鱼远望完成签到,获得积分10
10秒前
涤新完成签到 ,获得积分10
11秒前
传奇3应助zzy采纳,获得10
11秒前
12秒前
无花果应助Nemo采纳,获得10
12秒前
科研修沟发布了新的文献求助10
12秒前
13秒前
不准吃烤肉完成签到,获得积分10
14秒前
Zehn发布了新的文献求助10
14秒前
14秒前
ww发布了新的文献求助20
14秒前
彭于晏应助wang采纳,获得10
15秒前
1+1应助想多睡会儿采纳,获得10
15秒前
牛牛完成签到,获得积分10
15秒前
冷酷的如风完成签到,获得积分20
15秒前
16秒前
简默完成签到,获得积分10
17秒前
时光如梭发布了新的文献求助10
17秒前
NexusExplorer应助豆子采纳,获得10
18秒前
19秒前
19秒前
20秒前
20秒前
高分求助中
Earth System Geophysics 1000
Semiconductor Process Reliability in Practice 650
Studies on the inheritance of some characters in rice Oryza sativa L 600
Medicina di laboratorio. Logica e patologia clinica 600
《关于整治突出dupin问题的实施意见》(厅字〔2019〕52号) 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
Language injustice and social equity in EMI policies in China 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3207318
求助须知:如何正确求助?哪些是违规求助? 2856706
关于积分的说明 8106534
捐赠科研通 2521854
什么是DOI,文献DOI怎么找? 1355242
科研通“疑难数据库(出版商)”最低求助积分说明 642199
邀请新用户注册赠送积分活动 613478