No abstract

This work proposes a novel precision motion control framework of robotized industrial hydraulic excavators via datadriven model inversion. Rather than employing a single neural network to approximate the whole excavator dynamics, including input delays and dead-zones, we construct a physics-inspired datadriven model with a modular structure. The data-driven model is then inverted in a modular fashion which benefits the training speed. The data-driven model and its inversion are trained offline in a supervised manner using the real operational data since online learning methods can damage the machine and surroundings. The entire motion control framework consists of the data-driven model inversion that compensates for the excavator dynamics and the proportional control that determines the input of the model inversion to enhance the robustness. The framework is experimentally validated with a commercial 38-ton class hydraulic excavator for digging and grading tasks, achieving a precise control performance (i.e., root-mean-square of the path following error under 2 [cm]) even under severe soil interactions.

We propose a novel teleoperation framework for multiple distributed non-holonomic mobile robots (WMR), each equipped with onboard sensing and computing using peer-to-peer communication. One of the WMRs is designated as the leader with the first-person view camera and SLAM, while the other WMRs maintain a certain desired formation relative to their respective fore-running WMR in a distributed manner. For this, we first utilize nonholonomic passive decomposition to split the platoon kinematics into that of the formation-keeping aspect and the collective tele-driving aspect. We then design the controls for these two aspects individually and distribute them into each WMR while incorporating their nonholonomic constraint and distribution requirement. We also propose a novel predictive display, which, by providing the user with the estimated current and predicted future pose of the platoon and future possibility of collision while incorporating the uncertainty inherent to the distribution, can significantly enhance the tele-driving performance. Experiments and user study are also performed.

No abstract

No abstract