No abstract

In many industrial robotics applications, such as spot-welding, spray-painting or drilling, the robot is required to visit successively multiple targets. The robot travel time among the targets is a significant component of the overall execution time. This travel time is in turn greatly affected by the order of visit of the targets, and by the robot configurations used to reach each target. Therefore, it is crucial to optimize these two elements, a problem known in the literature as the Robotic Task Sequencing Problem (RTSP). Our contribution in this paper is two-fold. First, we propose a fast, near-optimal, algorithm to solve RTSP. The key to our approach is to exploit the classical distinction between task space and configuration space, which, surprisingly, has been so far overlooked in the RTSP literature. Second, we provide an open-source implementation of the above algorithm, which has been carefully benchmarked to yield an efficient, ready-to-use, software solution. We discuss the relationship between RTSP and other Traveling Salesman Problem (TSP) variants, such as the Generalized Traveling Salesman Problem (GTSP), and show experimentally that our method finds motion sequences of the same quality but using several orders of magnitude less computation time than existing approaches.

This paper presents the first successful experiment implementing whole-body model predictive control with state feedback on a torque-control humanoid robot. We demonstrate that our control scheme is able to do whole-body target tracking, control the balance in front of strong external perturbations and avoid collision with an external object. The key elements for this success are threefold. First, optimal control over a receding horizon is implemented with Crocoddyl, an optimal control library based on differential dynamics programming, providing state-feedback control in less than 10 ms. Second, a warm start strategy based on memory of motion has been implemented to overcome the sensitivity of the optimal control solver to initial conditions. Finally, the optimal trajectories are executed by a low-level torque controller, feedbacking on direct torque measurement at high frequency. This paper provides the details of the method, along with analytical benchmarks with the real humanoid robot Talos.A video of the experiment is available at https://peertube.laas.fr/videos/watch/cbc25927-337c-4635-a1bc-153b9aeb4135

Conventional hybrid automatic speech recognition (ASR) engines exploit state-ofthe-art Deep Neural Network (DNN) based acoustic model (AM) trained with Lattice Free-Maximum Mutual Information (LF-MMI) criterion and n-gram Language Model (LM). These systems usually have a large number of parameters and therefore require significant parameter reduction to operate on embedded devices. This thesis studies an impact of the parameter reduction on the overall speech recognition performance. Following three approaches are presented: (i) AM trained in the Kaldi framework with conventional factorized TDNN (TDNN-F) architecture. (ii) the TDNN built in Kaldi is loaded into the Pytorch toolkit using a C++ wrapper. The weights and activation parameters are then quantized and the inference is performed in Pytorch. (iii) post quantization training for fine-tuning. Results obtained on standard Librispeech setup provide an interesting overview of recognition accuracy with respect to applied quantization schemes. Furthermore, this thesis revisits Keyword Spotting (KWS) approaches and demonstrates that LF-MMI AM built to classify context-independent phones can operate well when integrated within a lightweight decoder providing a likelihood ratio based confidence score. The KWS was compared with the conventional lattice-based system on several keyword detection datasets.