• Corpus ID: 252367308

Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph

  title={Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph},
  author={Shuijing Liu and Peixin Chang and Zhe Huang and Neeloy Chakraborty and Kaiwen Hong and Weihang Liang and David Livingston McPherson and Junyi Geng and Katherine Rose Driggs-Campbell},
—We study the problem of safe and intention-aware robot navigation in dense and interactive crowds. Most previous reinforcement learning (RL) based methods fail to consider different types of interactions among all agents or ignore the intentions of people, which results in performance degradation. In this paper, we propose a novel recurrent graph neural network with attention mechanisms to capture heterogeneous interactions among agents through space and time. To en-courage longsighted robot… 

Figures and Tables from this paper



Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning

This work proposes to rethink pairwise interactions with a self-attention mechanism, and jointly model Human-Robot as well as Human-Human interactions in the deep reinforcement learning framework, and captures the Human- human interactions occurring in dense crowds that indirectly affects the robot’s anticipation capability.

Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning

Decentralized structural-Recurrent Neural Network (DS-RNN), a novel network that reasons about spatial and temporal relationships for robot decision making in crowd navigation, is proposed and demonstrated that it outperforms previous methods in challenging crowd navigation scenarios.

Relational Graph Learning for Crowd Navigation

This work presents a relational graph learning approach for robotic crowd navigation using model-based deep reinforcement learning that plans actions by looking into the future and uses a Graph Convolutional Network to encode higher-order interactions in each agent’s state representation.

Robot Navigation in Crowds by Graph Convolutional Networks With Attention Learned From Human Gaze

This work trains a graph convolutional network based on human gaze data that accurately predicts human attention to different agents in the crowd as they perform a navigation task based on a top down view of the environment and incorporates the learned attention into a graph-based reinforcement learning architecture.

Mobile Robot Navigation Using Learning-Based Method Based on Predictive State Representation in a Dynamic Environment

A deep reinforcement learning method is applied based on a novel predictive state representation (PSR) model to mobile robot navigation for realizing a navigation method considering the changes in pedestrian behavior caused by robot actions and other pedestrians.

Towards Safe Navigation Through Crowded Dynamic Environments

  • Z. XiePujie XinP. Dames
  • Computer Science
    2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2021
This paper proposes a novel neural network-based control policy to enable a mobile robot to navigate safety through environments filled with both static obstacles, such as tables and chairs, and

Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction

Gumbel Social Transformer is proposed, in which an Edge Gumbel Selector samples a sparse interaction graph of partially detected pedestrians at each time step and a Node Transformer Encoder and a Masked LSTM encode pedestrian features with sampled sparse graphs to predict trajectories.

Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles

A new method is proposed that combines a deep socially aware attentive value network with a human multimodal trajectory prediction model to help identify the optimal driving policy and introduces a novel technique to extend the discrete action space with minimal additional computational requirements.

DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

This paper proposes a person detection network which uses an alternative strategy to combine scans obtained at different times, and follows a forward looking paradigm, Distance Robust SPatial Attention and Auto-regressive Model (DR-SPAAM).

Intent-Aware Pedestrian Prediction for Adaptive Crowd Navigation

It is shown that confidence of pedestrian prediction can be used to adjust the risk of a navigation policy adaptively to afford the most comfortable level as measured by the frequency of personal space violation in comparison with baselines.