Meta Preference Learning for Fast User Adaptation in Human-Supervisory Multi-Robot Deployments

  title={Meta Preference Learning for Fast User Adaptation in Human-Supervisory Multi-Robot Deployments},
  author={Chao Huang and Wenhao Luo and Rui Liu},
  journal={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  • Chao HuangWenhao LuoRui Liu
  • Published 14 March 2021
  • Computer Science
  • 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
As multi-robot systems (MRS) are widely used in various tasks such as natural disaster response and social security, people enthusiastically expect an MRS to be ubiquitous that a general user without heavy training can easily operate. However, humans have various preferences on balancing between task performance and safety, imposing different requirements onto MRS control. Failing to comply with preferences makes people feel difficult in operation and decreases human willingness of using an MRS… 

Figures from this paper

SIRL: Similarity-based Implicit Representation Learning

The ultimate goal is to enable robots to identify and isolate the causal features that people actually care about and use when they represent states and behavior.

Task Selection and Planning in Human-Robot Collaborative Processes: To be a Leader or a Follower?

A task selection and planning algorithm is proposed that enables the robot to consider the human’s preference to lead, as well as the team and the human's performance, and adapts itself accordingly by taking or giving the lead.

Smart Power Supply for UAV Agility Enhancement Using Deep Neural Networks

A novel intelligent power solution, Agility-Enhanced Power Supply (AEPS), was developed to proactively prepare appropriate amount powers at the right timing to support motion planning with enhanced agility, and the safety of UAV in complex working environment will be enhanced.



and a at

The xishacorene natural products are structurally unique apolar diterpenoids that feature a bicyclo[3.3.1] framework. These secondary metabolites likely arise from the well-studied, structurally

Active Preference Learning using Maximum Regret

This work proposes a query selection that greedily reduces the maximum error ratio over the solution space and demonstrates that the proposed approach outperforms other state of the art techniques in both learning efficiency and ease of queries for the user.

and s

Asking Easy Questions: A User-Friendly Approach to Active Reward Learning

This paper explores an information gain formulation for optimally selecting questions that naturally account for the human's ability to answer, and determines when these questions become redundant or costly.

Multi-Robot Persistent Surveillance With Connectivity Constraints

In simulation studies, a short horizon greedy approach can outperform a full horizon approach, and it is shown that partitioning the area and applying the tree traversal approach can achieve a similar performance to the unpartitioned case up to a certain number of robots but requires less optimization time.

Bringing Adaptive and Immersive Interfaces to Real-World Multi-Robot Scenarios: Application to Surveillance and Intervention in Infrastructures

The design and development of an adaptive and immersive interface using virtual reality to bring operators into scenarios and allow an intuitive commanding of robots, as well as a complete set of experiments carried out to establish comparisons with a conventional one.

I and J

Teacher-Aware Active Robot Learning

This paper proposes a learning strategy that aims to minimize the user's workload by taking into account the flow of the questions and reports results from both the robot's performance and the human teacher's perspectives, observing how the hybrid strategy represents a good compromise between learning performance and user's experienced workload.

Interaction Algorithm Effect on Human Experience with Reinforcement Learning

The results show an agent that learns from action advice creates a better user experience compared to an agent That learns from binary critique in terms of frustration, perceived performance, transparency, immediacy, and perceived intelligence.

Optimized flocking of autonomous drones in confined environments

This paper numerically demonstrated that the induced swarm behavior remained stable under realistic conditions for large flock sizes and notably for large velocities, and showed that coherent and realistic collective motion patterns persisted even around perturbing obstacles.