Optimal decision making in robotic assembly and other trial-and-error tasks

by   James Watson, et al.

Uncertainty in perception, actuation, and the environment often require multiple attempts for a robotic task to be successful. We study a class of problems providing (1) low-entropy indicators of terminal success / failure, and (2) unreliable (high-entropy) data to predict the final outcome of an ongoing task. Examples include a robot trying to connect with a charging station, parallel parking, or assembling a tightly-fitting part. The ability to restart after predicting failure early, versus simply running to failure, can significantly decrease the makespan, that is, the total time to completion, with the drawback of potentially short-cutting an otherwise successful operation. Assuming task running times to be Poisson distributed, and using a Markov Jump process to capture the dynamics of the underlying Markov Decision Process, we derive a closed form solution that predicts makespan based on the confusion matrix of the failure predictor. This allows the robot to learn failure prediction in a production environment, and only adopt a preemptive policy when it actually saves time. We demonstrate this approach using a robotic peg-in-hole assembly problem using a real robotic system. Failures are predicted by a dilated convolutional network based on force-torque data, showing an average makespan reduction from 101s to 81s (N=120, p<0.05). We posit that the proposed algorithm generalizes to any robotic behavior with an unambiguous terminal reward, with wide ranging applications on how robots can learn and improve their behaviors in the wild.


page 4

page 10


RoboAssembly: Learning Generalizable Furniture Assembly Policy in a Novel Multi-robot Contact-rich Simulation Environment

Part assembly is a typical but challenging task in robotics, where robot...

Learning a High-Precision Robotic Assembly Task Using Pose Estimation from Simulated Depth Images

Most of industrial robotic assembly tasks today require fixed initial co...

Elly: A Real-Time Failure Recovery and Data Collection System for Robotic Manipulation

Even the most robust autonomous behaviors can fail. The goal of this res...

Learning needle insertion from sample task executions

Automating a robotic task, e.g., robotic suturing can be very complex an...

Failure Prediction with Statistical Guarantees for Vision-Based Robot Control

We are motivated by the problem of performing failure prediction for saf...

D-optimal joint best linear unbiased prediction of order statistics

In life-testing experiments, it is often of interest to predict unobserv...

Please sign up or login with your details

Forgot password? Click here to reset