Planning and Learning are complementary approaches. Planning relies on deliberative reasoning about the current state and sequence of future reachable states to solve the problem. Learning, on the other hand, is focused on improving system performance based on experience or available data. Learning to improve the performance of planning based on experience in similar, previously solved problems, is ongoing research. One approach is to learn Value function (cost-to-go) which can be used as heuristics for speeding up search-based planning. Existing approaches in this direction use the results of the previous search for learning the heuristics. In this work, we present a search-inspired approach of systematic model exploration for the learning of the value function which does not stop when a plan is available but rather prolongs search such that not only resulting optimal path is used but also extended region around the optimal path. This, in turn, improves both the efficiency and robustness of successive planning. Additionally, the effect of losing admissibility by using ML heuristic is managed by bounding ML with other admissible heuristics.

This paper presents preliminary work on learning the search heuristic for the optimal motion planning for automated driving in urban traffic. Previous work considered search-based optimal motion planning framework (SBOMP) that utilized numerical or model-based heuristics that did not consider dynamic obstacles. Optimal solution was still guaranteed since dynamic obstacles can only increase the cost. However, significant variations in the search efficiency are observed depending whether dynamic obstacles are present or not. This paper introduces machine learning (ML) based heuristic that takes into account dynamic obstacles, thus adding to the performance consistency for achieving real-time implementation.

This paper presents a framework for fast and robust motion planning designed to facilitate automated driving. The framework allows for real-time computation even for horizons of several hundred meters and thus enabling automated driving in urban conditions. This is achieved through several features. Firstly, a convenient geometrical representation of both the search space and driving constraints enables the use of classical path planning approach. Thus, a wide variety of constraints can be tackled simultaneously (other vehicles, traffic lights, etc.). Secondly, an exact cost-to-go map, obtained by solving a relaxed problem, is then used by A*-based algorithm with model predictive flavour in order to compute the optimal motion trajectory. The algorithm takes into account both distance and time horizons. The approach is validated within a simulation study with realistic traffic scenarios. We demonstrate the capability of the algorithm to devise plans both in fast and slow driving conditions, even when full stop is required.

For almost a decade, energy efficient driving occupies the attention of researchers and engineers. Still the consideration of overtaking in eco-driving didn’t receive a lot of attention yet. In this work energy efficient driving of (semi)autonomous electric vehicles operating in environment with other traffic participants is studied. Neglecting the constraints imposed from the surrounding traffic, when generating an energy optimal speed trajectory may lead to trajectories which are not attainable in real driving situation which may eventually lead to bigger energy consumption and low driver acceptance. An existing approach, which considers other traffic participants and optimizes the overtaking problem, modifies a previously generated unconstrained trajectory to satisfy constraints arisen from surrounding traffic. In contrast to this, the proposed approach incorporates a leading vehicle’s motion as constraint in original optimal control problem. By this approach the generated trajectory is globally optimal. Besides that, this approach considers overtaking decision making and leaves possibility to not overtake at all.

This paper proposes an approach of digital controller design on microcontrollers based on control surface disretization. As experimental setup a simple system composed of a DC motor, the PWM drive and a encoder was built. Identification of this simple system was done using the first order linear model and the Hammerstein-Wiener model. The quality of these models was compared based on the fitness function and their ability to cope with system nonlinearities. A discrete PI speed controller was designed based on the Hammerstein-Wiener model and tuned by the Gauss-Newton optimization algorithm. The Fuzzy logic controller was designed on the basis of the PI controller behaviour with genetic algorithm parameter tuning. The control surface of the Fuzzy logic controller was discretized for microcontroller implementation. Both controllers were implemented on the Arduino Mega platform and their control performances were tested and compared.