No abstract

Many works have recently explored Sim-to-real transferable visual model predictive control (MPC). However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-real transfer, which remains a significant human effort in transferring the models learned in simulations to new domains in the real world.To alleviate this problem, we first propose a novel modellearning framework called Kalman Randomized-to-Canonical Model (KRC-model). This framework is capable of extracting task-relevant intrinsic features and their dynamics from randomized images. We then propose Kalman Randomized-to-Canonical Model Predictive Control (KRC-MPC) as a zeroshot sim-to-real transferable visual MPC using KRC-model. The effectiveness of our method is evaluated through a valve rotation task by a robot hand in both simulation and the real world, and a block mating task in simulation. The experimental results show that KRC-MPC can be applied to various real domains and tasks in a zero-shot manner.

This paper presents the implementation of maximum hands-off distributed control in a quadrotor group. We assume that individual quadrotors can only communicate with neighbouring quadrotors to obtain state information and do not know the state of the whole group. The maximum hands-off distributed control is an extension of the consensus control using sparse optimal control. It converges the state of a group using only local information while maximising the time when the control input is zero by optimising the consensus control input through sparse optimisation. This minimises the time required for control and reduces energy consumption. We applied this control to a four-quadrotor group using MATLAB and CoppeliaSim simulations. The results confirm that the four quadrotors converged to the same state and the control inputs became sparse. Experiments using four small Tello EDU quadrotors further confirmed that they could reach the same altitude using the maximum hands-off distributed controller.

This paper considers the problem of estimating a preferred food arrangement for users from interactive pairwise comparisons using Computer Graphics (CG)-based dish images. As a foodservice industry requirement, we need to utilize domain rules for the geometry of the arrangement (e.g., the food layout of some Japanese dishes is reminiscent of mountains). However, those rules are qualitative and ambiguous; the estimated result might be physically inconsistent (e.g., each food physically interferes, and the arrangement becomes infeasible). To cope with this problem, we propose Physically Consistent Preferential Bayesian Optimization (PCPBO) as a method that obtains physically feasible and preferred arrangements that satisfy domain rules. PCPBO employs a bi-level optimization that combines a physical simulation-based optimization and a Preference-based Bayesian Optimization (PbBO). Our experimental results demonstrated the effectiveness of PCPBO on simulated and actual human users.

No abstract