There are 2 repositories under social-navigation topic.
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
Pedestrian simulator powered by the social force model
A curated list of robot social navigation.
[T-RO 2023] DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles
Extended Social Force Model in Python for social navigation research
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs (CVPR 2019)
Pedestrian ROS simulator with Gazebo and differential wheeled robots
Code base for SICNav T-RO paper and SICNav-Diffusion RA-L paper
SocialGym 2: A lightweight benchmark and simulator for multi-robot social navigation using ROS and the OpenAI gym.
(IJRR) Mixed Strategy Nash Equilibrium for Crowd Navigation
Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space (IEEE-IV-2024)
Socially normative mobile robot navigation
(RSS 2021) Move Beyond Trajectories: Distribution Space Coupling for Crowd Navigation
This is a online social robot navigation framework that implements several techniques for that matter, like the social relevance validity checking and an extended social comfort cost function.
An infrastructure built using PyGame and OpenAI Gymnasium used to train robots within a social navigation context with a wide range of human motion models to simulate crowds of pedestrians.
(ICRA 2025) Inverse Mixed Strategy Games with Generative Trajectory Models
Socially Aware Robot Navigation on Ros with Turtlebot3
This repository is an upgraded version of the pedsim_ros package, mainly featuring the addition of robot spawning capability during the pedestrian simulation.
Adaptive social controller algorithms with Deep Reinforcement Learning.
TD3-Based Socially Aware Robot Navigation in Dynamic Environments
Human-Aware Navigation in diverse context, based on the localization of human with a leg detector.
A JAX based implementation of the Optimal Reciprocal Collision Avoidance (ORCA) in Python.
This repository contains two Gazebo plugins for simulation crowd motion: one is the classical Social Force Model and the other is the Headed Social Force Model, where also the orientation of each pedestrian is taken into account.