Socially Compliant Navigation in dense crowds

Navigating in complex and highly dynamic environments such as crowds is still a major challenge for autonomous vehicle such as autonomous wheelchairs or even autonomous cars. This article presents a new way of navigating in crowds by using behavioral clustering for the surrounding agents and representing the crowd as a set of moving polygons. Once the environment has been modelled in this way and the robot has all the information it needs, we then propose a navigation algorithm that is able to guide the vehicle through the scene. The key-points of this algorithm are that (1) it can avoid densely-populated areas in order to minimize the risk of being on a collision course with any of the surrounding dynamic obstacles, (2) it generates socially compliant trajectories.

• Publication year

  2019

• Venue

  2019 IEEE Intelligent Vehicles Symposium (IV)

• Publication date

  2019-06-09

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/IVS.2019.8814288
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• The navigation procedure is intended to generate socially compliant trajectories.

  Confidence 0.90

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review
• The crowd navigation algorithm is designed to guide the vehicle through the scene while avoiding densely-populated areas to reduce collision risk.

  Confidence 0.92

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review
• Behavioral clustering of surrounding agents and a moving-polygon representation are used to model the crowd environment.

  Confidence 0.96

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review

• behavioral clustering

  method

  A grouping approach that clusters surrounding agents according to observed behavior in the crowd scene.

  Aliases: agent behavioral clustering

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review
• crowd navigation algorithm

  algorithm, planning method

  The planning procedure that computes a vehicle path through the crowd scene.

  Aliases: navigation planner

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review
• densely-populated areas

  scene region, environment feature

  Parts of the scene where many agents are concentrated close together.

  Aliases: crowded zones

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review
• moving polygons

  representation, model

  A geometric representation that models the crowd as a set of polygons that move over time.

  Aliases: moving-polygon crowd model

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review
• socially compliant trajectories

  trajectory, output

  Vehicle trajectories that are shaped to respect social navigation norms around pedestrians.

  Aliases: socially compliant paths

  박진우 (dztg5apj7m) extractionB (s683577b42) reviewGahyoun (29ua5897xm) review

• Mapping likelihood of encountering humans: Application to path planning in crowded environment

  2017cited by this paper
• EACS: Effective Avoidance Combination Strategy

  2017cited by this paper
• Robot navigation in dense human crowds: the case for cooperation

  2013cited by this paper
• Path planning with obstacle avoidance based on visibility binary tree algorithm

  2013cited by this paper
• Optimal Reciprocal Collision Avoidance for Multiple Non-Holonomic Robots

  2010cited by this paper
• Risk based motion planning and navigation in uncertain dynamic environment

  2010cited by this paper
• Probabilistic navigation in dynamic environment using Rapidly-exploring Random Trees and Gaussian processes

  2008cited by this paper
• A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise

  1996cited by this paper
• Social force model for pedestrian dynamics.

  1995cited by this paper
• Robot navigation in unknown generalized polygonal terrains using vision sensors

  1995cited by this paper
• Low Cost P erception of Dense Moving Crowd Clusters for Appropriate Navigation *

  year unknowncited by this paper

• Minimally-intrusive Navigation in Dense Crowds with Integrated Macro and Micro-level Dynamics

  2023cites this paper
• A Unified Multiple-Motion-Mode Framework for Socially Compliant Navigation in Dense Crowds

  2022cites this paper
• Autonomous Robot Navigation in Crowd

  2022cites this paper
• Risk Assessment by a Passenger of an Autonomous Vehicle Among Pedestrians: Relationship Between Subjective and Physiological Measures

  2021cites this paper
• Cooperative and Human-aware Robot Navigation in Dynamic Environments

  2017cites this paper