Intention-aware online POMDP planning for autonomous driving in a crowd

By Haoyu Bai, Shaojun Cai, Nan Ye, David Hsu, Wee Sun Lee. IEEE International Conference on Robotics and Automation, 2015

348 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Social Psychology

View Paper: https://www.semanticscholar.org/paper/481aa2882a5816686a5bea7db755862cded42081

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

In Social Psychology

Citations in the corpus

Human motion trajectory prediction: a survey (2019, methodology): “This category includes several physics-based approaches (Zhu 1991; Elnagar and Gupta 1998; Elnagar 2001; Foka and Trahanias 2010; Schneider and Gavrila 2013; Bai et al. 2015; Pettr ´ e et al. 2009).”
Autonomous Vehicles That Interact With Pedestrians: A Survey of Theory and Practice (2018, background): “onds travel time to the destination [139].”
A Survey of State-Action Representations for Autonomous Driving (2018, background): “This representation is used in (Forbes et al., 1995; Wheeler et al., 2015; Bai et al., 2015; Gindele et al., 2015; Song et al., 2016; Sunberg et al., 2017; Paxton et al., 2017; Lee and Seo, 2017; Shalev-Shwartz et al., 2017; Galceran et al., 2017; Chen et al., 2017; Paxton et al., 2017).”
PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction (2019, background): “Intention, defined as the potential goal (destination) of pedestrians, is used to refine predicted trajectories [3, 29, 2, 30].”
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction (2021, background): “…the observed trajectories of pedestrians, pedestrian trajectory prediction aims to predict a sequence of future location coordinates of pedestrians, which plays a critical role in various applications like autonomous driving [3, 29], video surveillance [28, 45] and visual recognition [9, 27, 16].”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, methodology): “An online POMDP approach is used in [362] to drive the car through the crowd safely, but planning at 3 Hz cannot make it possible to implement in the real trafﬁc.”
Core Challenges of Social Robot Navigation: A Survey (2021, background): “Coupling prediction and planning creates a broad theoretical umbrella: joint probability distributions, braid dynamics, interactive partially observable Markov decision processes (POMDPs), game-theoretic approaches, and coupled dynamical systems are all specific coupled prediction and planning formu”
Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction (2020, background): “For example, it is a critical component for collision avoidance systems or emergency braking systems [2, 18, 16, 22].”
Socially aware motion planning with deep reinforcement learning (2017, background): “In particular, researchers have explored using robots to provide personal mobility services and luggage carrying support in complex, pedestrian-rich environments (e.g., airports and shopping malls) [1].”
Learning with Humans in the Loop (2020, methodology): “ON THE UTILITY OF MODEL LEARNING IN HUMAN-ROBOT INTERACTION 8 reinforcement learning, and the ToM-based method will plan the robot’s actions using the learned model.”
Human-Like Decision Making for Autonomous Driving: A Noncooperative Game Theoretic Approach (2020, background): “In [6], a robust decision-making approach is studied using partially observable MDP considering uncertain measurements, which can make AVs move safely and efficiently amid pedestrians.”
DESPOT: Online POMDP Planning with Regularization (2013, background): “It achieved real-time performance on this system (Bai, Cai, Ye, Hsu, & Lee, 2015).”