Adaptive Simplex Architecture for Safe, Real-Time Robot Path Planning.

Tudor B. Ionescu

doi:10.3390/s21082589

Abstract

The paper addresses the problem of using machine learning in practical robot applications, like dynamic path planning with obstacle avoidance, so as to achieve the performance level of machine learning model scorers in terms of speed and reliability, and the safety and accuracy level of possibly slower, exact algorithmic solutions to the same problems. To this end, the existing simplex architecture for safety assurance in critical systems is extended by an adaptation mechanism, in which one of the redundant controllers (called a high-performance controller) is represented by a trained machine learning model. This model is retrained using field data to reduce its failure rate and redeployed continuously. The proposed adaptive simplex architecture (ASA) is evaluated on the basis of a robot path planning application with dynamic obstacle avoidance in the context of two human-robot collaboration scenarios in manufacturing. The evaluation results indicate that ASA enables a response by the robot in real time when it encounters an obstacle. The solution predicted by the model is economic in terms of path length and smoother than analogous algorithmic solutions. ASA ensures safety by providing an acceptance test, which checks whether the predicted path crosses the obstacle; in which case a suboptimal, yet safe, solution is used.

Highlights

Robot applications involve motion planning problems, for many of which there exist machine learning (ML) model-based approaches
The model is scored 6000 times, because the path between the origin and target is divided into 100 segments
This paper introduced the adaptive simplex architecture (ASA) for robotics applications, which extends the original simplex architecture from the domain of reliability engineering by enabling the use of machine learning-based solutions to common robotics problems, like path and trajectory planning with and without obstacle avoidance

Summary

Introduction

Robot applications involve motion planning problems, for many of which there exist machine learning (ML) model-based approaches (e.g., collision-free path and trajectory planning, assembly, bin picking and placing, etc.). ML is typically used when a computational algorithm does not exist or would be impractical (e.g., due to complexity of error proneness), ML-based solutions to problems that allow computational algorithms provide advantages in terms of performance thanks to the time-efficiency of machine learning model scorers (i.e., algorithms that process trained ML models to produce predictions for given inputs)

Results

Discussion

Conclusion