Action Prediction in Humans and Robots

TL;DR

This paper presents an action prediction algorithm that encodes actions as event sequences, demonstrating comparable prediction timing between humans and robots, thereby enhancing natural human-robot collaboration.

Contribution

The study introduces a novel event-based encoding method for action prediction and shows its effectiveness in aligning robot predictions with human timing in collaborative tasks.

Findings

Humans and robots predict actions at similar events in most cases.

The algorithm achieves less than 60% of the action sequence passing before prediction.

Predictions improve the timing and naturalness of human-robot interactions.

Abstract

Efficient action prediction is of central importance for the fluent workflow between humans and equally so for human-robot interaction. To achieve prediction, actions can be encoded by a series of events, where every event corresponds to a change in a (static or dynamic) relation between some of the objects in a scene. Manipulation actions and others can be uniquely encoded this way and only, on average, less than 60% of the time series has to pass until an action can be predicted. Using a virtual reality setup and testing ten different manipulation actions, here we show that in most cases humans predict actions at the same event as the algorithm. In addition, we perform an in-depth analysis about the temporal gain resulting from such predictions when chaining actions and show in some robotic experiments that the percentage gain for humans and robots is approximately equal. Thus, if robots use this algorithm then their prediction-moments will be compatible to those of their human interaction partners, which should much benefit natural human-robot collaboration.