A Novel Training and Collaboration Integrated Framework for Human–Agent Teleoperation

Abstract

Human operators have the trend of increasing physical and mental workloads when performing teleoperation tasks in uncertain and dynamic environments. In addition, their performances are influenced by subjective factors, potentially leading to operational errors or task failure. Although agent-based methods offer a promising solution to the above problems, the human experience and intelligence are necessary for teleoperation scenarios. In this paper, a truncated quantile critics reinforcement learning-based integrated framework is proposed for human–agent teleoperation that encompasses training, assessment and agent-based arbitration. The proposed framework allows for an expert training agent, a bilateral training and cooperation process to realize the co-optimization of agent and human. It can provide efficient and quantifiable training feedback. Experiments have been conducted to train subjects with the developed algorithm. The performances of human–human and human–agent cooperation modes are also compared. The results have shown that subjects can complete the tasks of reaching and picking and placing with the assistance of an agent in a shorter operational time, with a higher success rate and less workload than human–human cooperation.

A Systematic Review of In-Vehicle Physiological Indices and Sensor Technology for Driver Mental Workload Monitoring

“…In recent years, the concept of MWL has been researched in several domains to understand the performance limits of humans. For instance, researchers have found that teleoperation tasks cause a trend of an increased MWL that is usually affected by subjective factors [ 7 ]. The increase in the MWL can potentially lead to errors, leading to failure in task completion.…”

AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System

“…With the advancement of data-driven approaches for robot manipulation [12,18], there is a growing need to collect human demonstrations in robotics. To enable easy and scalable data collection, teleoperation has also gained attention in simulated environments [60,32,56,14,8].…”

Learning to Assist Bimanual Teleoperation Using Interval Type-2 Polynomial Fuzzy Inference

“…A supervised teleoperation scheme can allow the robot to follow human commands [1]- [3]. Similarly, the robotic agent of [4] assists in trajectory training for novices based on task-dependent reinforcement learning. From a cognitive perspective, robots could be made more flexible and better interact with human users by learning from human movements humans using logical inference.…”