Skip to content

Experiments of the "Multi-Agent Trajectory Planning with NUV Priors" paper

License

Notifications You must be signed in to change notification settings

biaslab/MultiAgentTrajectoryPlanning

Repository files navigation

Multi-Agent Trajectory Planning with NUV Priors

By Bart van Erp, Dmitry Bagaev, Albert Podusenko Ismail Senoz and Bert de Vries


Abstract

This paper presents a probabilistic model-based approach to centralized multi-agent trajectory planning. This approach allows for incorporating uncertainty of the state and dynamics of the agents directly in the model. Probabilistic inference is then efficiently automated using message passing. The recently introduced normal-with-unknown-variance (NUV) priors are used to prevent collisions between agents and obstacles. Furthermore, a new expectation-maximization inference scheme is presented for box and halfspace priors, which takes state uncertainty into account when avoiding collisions.


This repository contains all experiments of the paper.

Installation instructions

  1. Install Julia

  2. activate environment (using ] and backspace you can switch between the regular prompt and package manager)

>> ] activate .
  1. instantiate environment (only required once)
>> ] instantiate
  1. start Pluto
>> using Pluto; Pluto.run()

License

MIT License Copyright (c) 2023 BIASlab

About

Experiments of the "Multi-Agent Trajectory Planning with NUV Priors" paper

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages