computer-vision-5

Social Navigation

3260 papers • 126 benchmarks • 313 datasets

This task studies how to navigate robot(s) among humans in a safe and socially acceptable way.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in social-navigation-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find social-navigation-10 models and implementations

facebookresearch/habitat-api

2 papers 1,693

Datasets

HabiCrowd

Subtasks

No subtasks available.

Most implemented papers

Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots

Z. Kira, Mrinal Kalakrishnan, Dhruv Batra, So Yeon Min, Vincent-Pierre Berges, Alexander Clegg, John Turner, Eric Undersander, Andrew Szot, Xavi Puig, Mikael Dallaire Cote, Tsung-Yen Yang, Ruslan Partsey, Ruta Desai, Michal Hlavac, Vladimír Vondruš, Théophile Gervet, Oleksandr Maksymets, Devendra Jitendra Malik, Singh Chaplot, Unnat Jain, †. AksharaRai, †. RoozbehMottaghi•Wed Oct 18 2023

Habitat 3.0 unlocks interesting new features in simulators for Embodied AI, and the authors hope it paves the way for a new frontier of embodied human-AI interaction capabilities.

Content

212 0

Paper Graph

Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning

S. Savarese, Roberto Martín-Martín, Claudia P'erez-D'Arpino, Can Liu, P. Goebel•Thu Oct 15 2020

A compositional principle for multi-layout training is explored and it is found that policies trained in a small set of geometrically simple layouts successfully generalize to more complex unseen layouts that exhibit composition of the structural elements available during training.

92 0

Paper Graph

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

Shuijing Liu, Peixin Chang, W. Liang, Neeloy Chakraborty, K. Driggs-Campbell•Sun Nov 08 2020

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.

140 0

Paper Graph

Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph

K. Driggs-Campbell, Shuijing Liu, Peixin Chang, Neeloy Chakraborty, Zhe Huang, Kaiwen Hong, Weihang Liang, D. McPherson, Junyi Geng•Wed Mar 02 2022

A novel recurrent graph neural network with attention mechanisms to capture heterogeneous interactions among agents through space and time to encourage longsighted robot behaviors and to prevent the robot from intruding into the intended paths of other agents.

113 0

Paper Graph

Social and Scene-Aware Trajectory Prediction in Crowded Spaces

Matteo Lisotto, Pasquale Coscia, Lamberto Ballan•Wed Sep 18 2019

An LSTM (long short-term memory)-based model is constructed considering three fundamental factors: people interactions, past observations in terms of previously crossed areas and semantics of surrounding space, which corroborate the effectiveness of the proposed framework in comparison to L STM-based models for human path prediction.

80 0

Paper Graph

Social Navigation with Human Empowerment Driven Deep Reinforcement Learning

H. V. Hoof, T. V. D. Heiden, Florian Mirus•Tue Mar 17 2020

This paper goes beyond the approach of classical \acf{RL} and provides an agent with intrinsic motivation using empowerment and demonstrates that a robot employing this approach strives for the empowerment of people in its environment, so they are not disturbed by the robot's presence and motion.

2 0

Paper Graph

Visual Navigation Among Humans With Optimal Control as a Supervisor

Varun Tolani, Somil Bansal, Aleksandra Faust, C. Tomlin•Thu Mar 19 2020

This work proposes an approach that combines learning-based perception with model-based optimal control to navigate among humans based only on monocular, first-person RGB images that can generalize to previously unseen environments and human behaviors, and transfer directly from simulation to reality.

43 0

Paper Graph

SoLo T-DIRL: Socially-Aware Dynamic Local Planner based on Trajectory-Ranked Deep Inverse Reinforcement Learning

Yifan Xu, Theodor Chakhachiro, Tribhi Kathuria, Maani Ghaffari•Thu Sep 15 2022

This work proposes a novel framework for socially-aware robot navigation in dynamic, crowded environments using a Deep Inverse Reinforcement Learning (DIRL) pipeline that outperforms the state-of-art social navigation methods in terms of the success rate, navigation time, and invasion rate.

5 0

Paper Graph

SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces

Rohan Chandra, Joydeep Biswas, Zayne Sprague, Jarrett Holtz•Wed Mar 08 2023

The SocialGym 2 simulator models multiple autonomous agents, replicating real-world dynamics in complex environments, including doorways, hallways, intersections, and roundabouts, and employs multi-agent reinforcement learning (MARL) to develop optimal navigation policies for multiple robots with diverse, dynamic constraints incomplex environments.

12 0

Paper Graph

SocNavGym: A Reinforcement Learning Gym for Social Navigation

Luis J. Manso, P. Bachiller, Aditya Kapoor, Sushant Swamy•Wed Apr 26 2023

SocNavGym is an advanced simulation environment for social navigation that can generate a wide variety of social navigation scenarios and facilitates the development of intelligent social agents and shows that the agents trained using the data-driven reward function display more advanced social compliance in comparison to the heuristic-based reward function.

9 0

Paper Graph

Adding a benchmark result helps the community track progress.