Corpus ID: 236428730

Group-based Motion Prediction for Navigation in Crowded Environments

  title={Group-based Motion Prediction for Navigation in Crowded Environments},
  author={Allan Wang and Christoforos Mavrogiannis and Aaron Steinfeld},
We focus on the problem of planning the motion of a robot in a dynamic multiagent environment such as a pedestrian scene. Enabling the robot to navigate safely and in a socially compliant fashion in such scenes requires a representation that accounts for the unfolding multiagent dynamics. Existing approaches to this problem tend to employ microscopic models of motion prediction that reason about the individual behavior of other agents. While such models may achieve high tracking accuracy in… Expand

Figures and Tables from this paper


Socially competent navigation planning by deep learning of multi-agent path topologies
A novel, data-driven framework for planning socially competent robot behaviors in crowded environments that constitutes the basis for the design of a human-inspired probabilistic inference mechanism that predicts the topology of multiple agents' future trajectories, given observations of the context. Expand
Social Momentum: A Framework for Legible Navigation in Dynamic Multi-Agent Environments
This work designs a planning framework that aims at generating motion that clearly communicates an agent’s intended collision avoidance strategy rather than its destination, and reveals statistical evidence suggesting that multi-agent trajectories of lower topological complexity tend to facilitate inference for observers. Expand
Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation
It is concluded that a cooperation model is critical for safe and efficient robot navigation in dense human crowds and the salient characteristics of nearly any dynamic navigation algorithm. Expand
Dynamic Channel: A Planning Framework for Crowd Navigation
This work presents an approach, called Dynamic Channels, to solve the global to local quandary of real-time navigation in dense human environments, by formulating the path planning problem as graph-searching in the triangulation space. Expand
Group-Aware Robot Navigation in Crowded Environments
Simulation experiments show that group-aware policies, compared to baseline policies that neglect human groups, achieve greater robot navigation performance, minimize violation of social norms and discomfort, and reduce the robot’s movement impact on pedestrians. Expand
Socially compliant mobile robot navigation via inverse reinforcement learning
An extensive set of experiments suggests that the technique outperforms state-of-the-art methods to model the behavior of pedestrians, which also makes it applicable to fields such as behavioral science or computer graphics. Expand
Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
  • Michael Everett, Y. Chen, J. How
  • Computer Science, Engineering
  • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2018
This work extends the previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules, and introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. Expand
Socially Adaptive Path Planning in Human Environments Using Inverse Reinforcement Learning
This work proposes a framework for socially adaptive path planning in dynamic environments, by generating human-like path trajectory and evaluating the approach by deploying it on a real robotic wheelchair platform, and comparing the robot trajectories to human trajectories. Expand
Group Split and Merge Prediction With 3D Convolutional Networks
This work formulates this as a video prediction problem, where group splits or merges are predicted given a history of geometric social group shape transformations, and develops a modified C3D model that performs significantly better at predicting the occurrence of splits and merges. Expand
Socially-aware robot navigation: A learning approach
This paper learns a set of dynamic motion prototypes from observations of relative motion behavior of humans found in publicly available surveillance data sets and demonstrates that the learned behaviors are better in reproducing human relative motion in both criteria than a Proxemics-based baseline method. Expand