Context-aware multi-task learning for pedestrian intent and trajectory prediction

行人 弹道 背景(考古学) 任务(项目管理) 计算机科学 人工智能 人机交互 机器学习 运输工程 模拟 工程类 系统工程 地理 天文 物理 考古
作者
Farzeen Munir,Tomasz Piotr Kucner
出处
期刊:Transportation Research Part C-emerging Technologies [Elsevier BV]
卷期号:178: 105203-105203 被引量:20
标识
DOI:10.1016/j.trc.2025.105203
摘要

The advancement of socially-aware autonomous vehicles hinges on precise modeling of human behavior. Within this broad paradigm, the specific challenge lies in accurately predicting pedestrian’s trajectory and intention. Traditional methodologies have leaned heavily on historical trajectory data, frequently overlooking vital contextual cues such as pedestrian-specific traits and environmental factors. Furthermore, there is a notable knowledge gap as trajectory and intention prediction have largely been approached as separate problems, despite their mutual dependence. To bridge this gap, we introduce PTINet (Pedestrian Trajectory and Intention Prediction Network), which jointly learns the trajectory and intention prediction by combining past trajectory observations, local contextual features (individual pedestrian behaviors), and global features (signs, markings etc.). The efficacy of our approach is evaluated on widely used public datasets: JAAD, PIE and TITAN, where it has demonstrated superior performance over existing state-of-the-art models in trajectory and intention prediction. The results from our experiments and ablation studies robustly validate PTINet’s effectiveness in jointly exploring intention and trajectory prediction for pedestrian behavior modeling. The experimental evaluation indicates the advantage of using global and local contextual features for pedestrian trajectory and intention prediction. The effectiveness of PTINet in predicting pedestrian behavior paves the way for the development of automated systems capable of seamlessly interacting with pedestrians in urban settings https://github.com/munirfarzeen/PTINet . • In this work, we asked whether predicting one aspect (intention) without the other (trajectory) limits the understanding of pedestrian behavior. Our results support this hypothesis by showing improved performance using our joint prediction approach. • We developed a novel multi-task framework, PTINet, that combines Local Contextual Features (LCF), such as pedestrian-specific attributes, with Global Features (GF)from image data and optical flow to analyze complex spatial–temporal patterns. • We chose a traditional LSTM over more complex transformers due to lower resource demands. Despite its simplicity, our approach outperforms transformer-based models in predicting pedestrian behavior. • Extensive experiments and ablation studies on benchmark datasets show PTINet’s superior performance, significantly outperforming state-of-the-art prediction models.
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
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
DOC_XIONG的应助被哇哦采纳,获得10
刚刚
徐枘发布了新的文献求助10
刚刚
1秒前
stackheap完成签到,获得积分10
2秒前
2秒前
Hello的应助被drizzle采纳,获得10
2秒前
刻苦冰绿完成签到 ,获得积分10
3秒前
Lemon发布了新的文献求助10
4秒前
范晨是gay发布了新的文献求助10
4秒前
纯真的伟诚完成签到,获得积分10
4秒前
5秒前
Lownx完成签到,获得积分10
5秒前
6L96Y发布了新的文献求助10
7秒前
7秒前
充电宝的应助被优雅的松鼠采纳,获得10
8秒前
想人陪的毛巾完成签到,获得积分10
8秒前
8秒前
鳄鱼叁叁完成签到 ,获得积分10
8秒前
9秒前
10秒前
10秒前
夜枭完成签到,获得积分10
11秒前
酷波er的应助被马儿采纳,获得10
12秒前
生动的绮南完成签到,获得积分10
12秒前
12秒前
fox199753206完成签到,获得积分10
12秒前
14秒前
369ninja发布了新的文献求助10
15秒前
15秒前
Louis发布了新的文献求助10
15秒前
16秒前
16秒前
幽默的盼山完成签到,获得积分10
17秒前
传奇3的应助被徐枘采纳,获得10
17秒前
牛黄完成签到 ,获得积分10
17秒前
18秒前
18秒前
18秒前
19秒前
栗子完成签到,获得积分10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184267
求助须知:如何正确求助?哪些是违规求助? 9573323
关于积分的说明 21830790
捐赠科研通 7781314
什么是DOI,文献DOI怎么找? 3434307
关于科研通互助平台的介绍 2558389
邀请新用户注册赠送积分活动 2480817