Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation

By Pete Trautman, Jeremy Ma, Richard M. Murray, Andreas Krause. Int. J. Robotics Res., 2015

324 citations recorded by the source corpus.

We consider the problem of navigating a mobile robot through dense human crowds. We begin by exploring a fundamental impediment to classical motion planning algorithms called the “freezing robot problem”: once the environment surpasses a certain level of dynamic complexity, the planner decides that all forward paths are unsafe, and the robot freezes in place (or performs unnecessary maneuvers) to avoid collisions. We argue that this problem can be avoided if the robot anticipates human cooperation, and accordingly we develop interacting Gaussian processes, a prediction density that captures cooperative collision avoidance, and a “multiple goal” extension that models the goal-driven nature of human decision making. We validate this model with an empirical study of robot navigation in dense human crowds (488 runs), specifically testing how cooperation models effect navigation performance. The multiple goal interacting Gaussian processes algorithm performs comparably with human teleoperators in crowd densities nearing 0.8 humans/m2, while a state-of-the-art non-cooperative planner exhibits unsafe behavior more than three times as often as the multiple goal extension, and twice as often as the basic interacting Gaussian process approach. Furthermore, a reactive planner based on the widely used dynamic window approach proves insufficient for crowd densities above 0.55 people/m2. We also show that our non-cooperative planner or our reactive planner capture the salient characteristics of nearly any dynamic navigation algorithm. Based on these experimental results and theoretical observations, we conclude that a cooperation model is critical for safe and efficient robot navigation in dense human crowds.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/f5783d21492ceeec6cfcf42595d270dedbb91d5e

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories With GANs (2019, background): “In [18], interacting mixtures of Gaussian Processes (GPs) are used for predicting the whereabouts of goal-driven social agents in crowds, where the parameters are learned from training data.”
Socially aware motion planning with deep reinforcement learning (2017, background): “paths could mark a large portion of the space untraversable [9].”
Planning and Decision-Making for Autonomous Vehicles (2018, background): “Since an agent’s actions are interdependent on all other agents’ actions, an uncertainty explosion in future states arises and results in the freezingrobot problem (85) discussed in the robotics community.”
Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning (2020, background): “robot problem” [15], [16], in which the planner finds all solutions to be below certain threshold of safety or feasibility, causing the robot to stop and continuously replan while the pedestrians move.”
Core Challenges of Social Robot Navigation: A Survey (2021, methodology): “This phenomenon may effectively yield the freezing robot problem as described by Trautman et al. [226], who pointed out that a practical way to resolve it is to enable the robot to explicitly expect human cooperation.”