Points, Lines, Boxes, Polygons (also hollow), Ellipses, Circles. RayCasting, offsets, rotation, scaling, bounding box padding, flags for static and ghost/trigger bodies

Motion Planner for Self Driving Cars

List of commonly used robotics libraries and packages

My solution for udacity path planning project. This makes the car drive > 20 miles without collision without constraint violation

The official repo for NeurIPS 2021 paper 'Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks'

Python robot's kinematics library

RRT (Rapidly-Exploring Random Trees) using Dubins curve, with collision check in MATLAB

This is a structure allowing you to find suitable collision-candidates out of a bulk of sprites or similar very fast.

Code for our paper "Autonomous Navigation in Unknown Environments with Sparse Bayesian Kernel-based Occupancy Mapping".

A Hybrid-A* planner with early stopping for efficient path planning and extended motion primitives to account for the motion capabilities of the U-Shift II vehicle. Author: Oliver Schumann

Code for our ICRA paper "Autonomous Navigation in Unknown Environments with Sparse Kernel-based Occupancy Mapping"

Polar Collision Grids: Effective Interaction Modelling for Pedestrian Trajectory Prediction in Shared Space Using Collision Checks (ITSC 2023)

Tile based collision detection and response in MonoGame. Handles solid tiles, ground detection, platforms and slopes.

Asteroids game made using C# with SFML.net

Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space (IEEE-IV-2024) - Pedestrian Trajectory Prediction Part

CudaSoftCollisions is a library that allow you to detect self collisions in a tetrahedrical mesh that is deformed over time.

This package checks for collisions while offline with its own model. This is useful especially while checking collisions for situations where collision links are disabled for experiments (allowing moveit to collide links in the simulation, e.g. while testing DawnIK Solver).

A simple c++ header-only single file that uses the Separating Axis Theorem (SAT) to detect collisions between two Oriented Bounding Boxes (OBB) and generate contact points for vertex-face collisions and edge-edge collisions.

This repository shows how to build a quad tree in a squared map. This data structure can be used to check for collisions super efficiently. Used mainly in games.