Collective Conditioned Reflex: A Bio-Inspired Fast Emergency Reaction Mechanism for Designing Safe Multi-Robot Systems

  title={Collective Conditioned Reflex: A Bio-Inspired Fast Emergency Reaction Mechanism for Designing Safe Multi-Robot Systems},
  author={Zhen Zhao and Bowei He and Wenhao Luo and R. Liu},
  journal={IEEE Robotics and Automation Letters},
  • Zhen ZhaoBowei He R. Liu
  • Published 24 February 2022
  • Computer Science
  • IEEE Robotics and Automation Letters
A multi-robot system (MRS) is a group of coordinated robots designed to cooperate with each other and accomplish given tasks. Due to the uncertainties in operating environments, the system may encounter emergencies, such as unobserved obstacles, moving vehicles, and extreme weather. Animal groups such as bee colonies initiate collective emergency reaction behaviors such as bypassing obstacles and avoiding predators, similar to muscle conditioned reflex which organizes local muscles to avoid… 

Figures and Tables from this paper



Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

An adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination is presented.

From division of labor to the collective behavior of social insects

  • D. Gordon
  • Economics
    Behavioral Ecology and Sociobiology
  • 2015
‘Division of labor’ is a misleading way to describe the organization of tasks in social insect colonies, because there is little evidence for persistent individual specialization in task. Instead,

An Improved Method towards Multi-UAV Autonomous Navigation Using Deep Reinforcement Learning

This paper proposes a multi-agent deep deterministic policy gradient algorithm based on prioritized experience replay, namely PER-MADDPG, which has fast convergence speed and good convergence results, and has excellent autonomous navigation capabilities.

Continuous learning of emergent behavior in robotic matter

It is shown that the physical connection between the units is enough to achieve learning, and no additional communication or centralized information is required, and such a distributed learning approach can be easily scaled to larger assemblies.

Toward Safe Human–Robot Interaction: A Fast- Response Admittance Control Method for Series Elastic Actuator

A fast-response admittance control method for SEAs that achieves a better performance in SEA stiffness tracking with lower time delay and tracking error and is validated from both simulation and real-world experiments.

The influence of social environment on cooperation and conflict in an incipiently social bee, Ceratina calcarata

How mutual tolerance is produced, and the role of social environment in inducing cooperation in social groups, remains unstudied in many simple societies. In particular, maternal and sibling care and

Multi-Robot Flocking Control Based on Deep Reinforcement Learning

This paper studies a prioritized experience replay (PER) mechanism and proposes the Prioritized Experience Replay-MADDPG (PER-M ADDPG) algorithm, which has a faster convergence speed and enables the robot group to complete the flocking task in the environment with obstacles.

Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams

This work develops a competitive multi agent environment called FortAttack in which two teams compete against each other, and corroborates that modeling agents with Graph Neural Networks and training them with Reinforcement Learning leads to the evolution of increasingly complex strategies for each team.

Trust-Aware Emergency Response for A Resilient Human-Swarm Cooperative System

  • Yijiang PangRui Liu
  • Computer Science
    2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
  • 2021
A trust-aware reflective control (Trust-R), was developed for a robot swarm to understand the collaborative mission and calibrate its motions accordingly for better emergency response, validated by improved task performance and increased trust scores.

Learning for Safety-Critical Control with Control Barrier Functions

A machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system, ultimately achieving safe behavior.