A behavioural transformer for effective collaboration between a robot and a non-stationary human
This addresses a key challenge in robotics for enabling effective collaboration with humans who change their behavior over time, though it appears incremental as it builds on existing transformer and meta-learning approaches.
The paper tackles the problem of human-robot collaboration hindered by non-stationary human behavior, proposing a meta-learning framework and a transformer-based method called BeTrans that adapts faster to such behaviors than state-of-the-art techniques in simulated environments.
A key challenge in human-robot collaboration is the non-stationarity created by humans due to changes in their behaviour. This alters environmental transitions and hinders human-robot collaboration. We propose a principled meta-learning framework to explore how robots could better predict human behaviour, and thereby deal with issues of non-stationarity. On the basis of this framework, we developed Behaviour-Transform (BeTrans). BeTrans is a conditional transformer that enables a robot agent to adapt quickly to new human agents with non-stationary behaviours, due to its notable performance with sequential data. We trained BeTrans on simulated human agents with different systematic biases in collaborative settings. We used an original customisable environment to show that BeTrans effectively collaborates with simulated human agents and adapts faster to non-stationary simulated human agents than SOTA techniques.