How to Capture Human Preference: Commissioning of a Robotic Use-Case via Preferential Bayesian Optimisation

TL;DR

This paper demonstrates that Preferential Bayesian Optimization (PBO) effectively captures human expert preferences in robotic setup commissioning, outperforming traditional cost functions and enabling better decision-making in complex industrial tasks.

Contribution

The study shows PBO can successfully optimize robotic configurations based solely on human preferences, revealing limitations of expert-defined cost functions and proposing a preference-based cost function for conventional BO.

Findings

PBO achieves expert satisfaction in robotic setup commissioning.

Expert-designed cost functions do not fully align with expert decisions.

Preference-based cost functions outperform expert-designed ones in decision consistency.

Abstract

The popularity of Bayesian Optimization (BO) to automate or support the commissioning of engineering systems is rising. Conventional BO, however, relies on the availability of a scalar objective function. The latter is often difficult to define and rarely captures the nuanced judgement of expert operators in industrial settings. Preferential Bayesian Optimization (PBO) addresses this limitation by relying solely on pairwise preference feedback of a human expert, so-called duels. In this paper, we study PBO's capacity to commission a particular setup where a manipulator needs to push a block towards a target position. We benchmark state-of-the-art algorithms in both simulations and in the real world. Our results confirm that PBO can commission the set-up to the satisfaction of an expert operator whilst relying solely on binary preference feedback. To evaluate to what extend the same result can be achieved using conventional BO we investigate the experts decision consistency against an expert-designed cost function. Our study reveals that the experts fail to define a cost function that is in full agreement with their own decision process as witnessed in the PBO experiments. We then show that the auxiliary cost function that is constructed as a by-product of the PBO algorithms outperforms the expert-designed cost function in terms of decision consistency. Furthermore we demonstrate that this cost function can be used with conventional BO algorithms in an effort to reproduce the optimal design. This proofs the preference based cost function captures the experts' preferences perhaps more effectively than the experts could articulate preference themselves. In conclusion, we discuss downsides and propose directions for future research.