Trajectory Prediction for Autonomous Driving Using Spatial-Temporal Graph Attention Transformer

计算机科学 编码 推论 图形 人工智能 变压器 编码器 卷积神经网络 注意力网络 机器学习 理论计算机科学 工程类 电气工程 化学 电压 操作系统 基因 生物化学
作者
Kunpeng Zhang,Xiaoliang Feng,Lan Wu,Zhengbing He
出处
期刊:IEEE Transactions on Intelligent Transportation Systems [Institute of Electrical and Electronics Engineers]
卷期号:23 (11): 22343-22353 被引量:57
标识
DOI:10.1109/tits.2022.3164450
摘要

For autonomous vehicles driving on roads, future trajectories of surrounding traffic agents (e.g., vehicles, bicycles, pedestrians) are essential information. The prediction of future trajectories is challenging as the motion of traffic agents is constantly affected by spatial-temporal interactions from agents and road infrastructure. To take those interactions into account, this study proposes a Graph Attention Transformer (Gatformer) in which a traffic scene is represented by a sparse graph. To maintain the spatial and temporal information of traffic agents in a traffic scene, Convolutional Neural Networks (CNNs) are utilized to extract spatial features and a position encoder is proposed to encode the spatial features and the corresponding temporal features. Based on the encoded features, a Graph Attention Network (GAT) block is employed to model the agent-agent and agent-infrastructure interactions with the help of attention mechanisms. Finally, a Transformer network is introduced to predict trajectories for multiple agents simultaneously. Experiments are conducted over the Lyft dataset and state-of-the-art methods are introduced for comparison. The results show that the proposed Gatformer could make more accurate predictions while requiring less inference time than its counterparts.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Spine Lin完成签到,获得积分10
刚刚
1秒前
2秒前
3秒前
初之发布了新的文献求助10
3秒前
3秒前
3秒前
大林发布了新的文献求助10
3秒前
孟双发布了新的文献求助10
5秒前
筑城院发布了新的文献求助10
6秒前
丘比特应助王哈哈采纳,获得10
6秒前
HML发布了新的文献求助10
6秒前
传奇3应助Loooong采纳,获得10
6秒前
研友_Z1WrgL完成签到,获得积分10
7秒前
cgs关闭了cgs文献求助
7秒前
李爱国应助puppy采纳,获得30
7秒前
zyl发布了新的文献求助10
7秒前
嘻嘻发布了新的文献求助10
8秒前
8秒前
pcr163应助轻松的听白采纳,获得50
8秒前
领导范儿应助王怀存采纳,获得10
9秒前
9秒前
uu完成签到 ,获得积分10
9秒前
自知则知之完成签到,获得积分10
10秒前
10秒前
10秒前
愉快的雁开应助小王啵啵采纳,获得10
11秒前
iNk应助初之采纳,获得10
11秒前
12秒前
12秒前
Tina完成签到,获得积分10
12秒前
明亮沁完成签到 ,获得积分10
12秒前
djiwisksk66应助甜甜的亦寒采纳,获得10
12秒前
蓝橙发布了新的文献求助10
13秒前
yueyue完成签到,获得积分10
13秒前
13秒前
13秒前
14秒前
没有你沉发布了新的文献求助10
14秒前
小春发布了新的文献求助10
14秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970683
求助须知:如何正确求助?哪些是违规求助? 3515337
关于积分的说明 11178055
捐赠科研通 3250580
什么是DOI,文献DOI怎么找? 1795357
邀请新用户注册赠送积分活动 875790
科研通“疑难数据库(出版商)”最低求助积分说明 805166