In this paper, two active fault-tolerant control (AFTC) schemes dedicated to induction-motor drives in electric or hybrid vehicle powertrains are presented and compared. Fault detection and mitigation are merged to propose a robust algorithm against speed-sensor faults (fault is modeled as significant additional noise or an exponential type emulating a bias) leading to uncertainties in the measurement. The first architecture is a hybrid fault tolerant-control (FTC) with proportional-integral and H_∞ controllers; the second architecture is the generalized internal model control (GIMC) with a natural reconfiguration. Both are built to ensure resilience while keeping good dynamic performances. For each architecture, the speed-sensor fault detection is based on an extended Kalman filter (EKF) that generates a residual vector. The correction method is calculated differently for the two schemes specifically in the switching transition phase between the nominal and robust controllers. A comparative study is carried out between the two FTC schemes.

Innovative technologies and naturalistic driving data sources provide a great potential to develop reliable autonomous driving systems. Understanding the behaviors of surrounding vehicles is essential for improving safety and mobility of autonomous vehicles. Onboard sensors like Radar, Lidar and Camera are able to track surrounding vehicles motion and to get different features like position, velocity and yaw. This paper proposes a hybrid approach to integrate maneuver classification using neural networks and trajectory prediction using Long Short-term Memory (LSTM) networks to get the future positions of adjacent vehicles. In this study we use the Next Generation Simulation (NGSIM) public dataset that provides a real driving data. The proposed approach is validated experimentally using VEDECOM demonstrator data. The results demonstrate that the proposed approach is able to predict driver intention to change lanes on average 2.2 seconds in advance. The Root Mean Square (RMS) errors of lateral and longitudinal positions are 0.30 m and 3.1 m respectively. The results demonstrate a high performance compared to various existing methods.

Recent developments on micromanipulation and Internet technologies allow potential impacts on networked microautomation of small industrial products. However, reliable and efficient microteleoperation systems with haptic feedback over the Internet face strong problems due to microenvironment variations, the scaling effect problem between worlds with different physical characteristics, and time delays in communication lines. Taking into account these constraints, a force-reflecting macro-microteleoperator controller is designed based on the framework H_infin loop-shaping procedure approach. This approach allows a convenient way to tradeoff the robustness for a prespecified time delay margin, variation of force scaling factors, and uncertainties in environment models. The experimental results clearly show that the proposed approach ensures the stability robustness against time delays and scaling factors.