Cooperation without Coordination: Hierarchical Predictive Planning for Decentralized Multiagent Navigation

by   Rose E. Wang, et al.

Decentralized multiagent planning raises many challenges, such as adaption to changing environments inexplicable by the agent's own behavior, coordination from noisy sensor inputs like lidar, cooperation without knowing other agents' intents. To address these challenges, we present hierarchical predictive planning (HPP) for decentralized multiagent navigation tasks. HPP learns prediction models for itself and other teammates, and uses the prediction models to propose and evaluate navigation goals that complete the cooperative task without explicit coordination. To learn the prediction models, HPP observes other agents' behavior and learns to maps own sensors to predicted locations of other agents. HPP then uses the cross-entropy method to iteratively propose, evaluate, and improve navigation goals, under assumption that all agents in the team share a common objective. HPP removes the need for a centralized operator (i.e. robots determine their own actions without coordinating their beliefs or plans) and can be trained and easily transferred to real world environments. The results show that HPP generalizes to new environments including real-world robot team. It is also 33x more sample efficient and performs better in complex environments compared to a baseline. The video and website for this paper can be found at and


page 1

page 3

page 5

page 7

page 8


Towards Using Promises for Multi-Agent Cooperation in Goal Reasoning

Reasoning and planning for mobile robots is a challenging problem, as th...

Hierarchical Image-Goal Navigation in Real Crowded Scenarios

This work studies the problem of image-goal navigation, which entails gu...

Intrinsically-Motivated Goal-Conditioned Reinforcement Learning in Multi-Agent Environments

How can a population of reinforcement learning agents autonomously learn...

ViNG: Learning Open-World Navigation with Visual Goals

We propose a learning-based navigation system for reaching visually indi...

A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

Autonomous agents must learn to collaborate. It is not scalable to devel...

The Price of Governance: A Middle Ground Solution to Coordination in Organizational Control

Achieving coordination is crucial in organizational control. This paper ...

Competing Adaptive Networks

Adaptive networks have the capability to pursue solutions of global stoc...

Please sign up or login with your details

Forgot password? Click here to reset