For travelling from point A to point B, autonomous vehicles generate a route between the points. During the mission, the vehicle uses a motion planning and controls algorithm to follow the planned route while avoiding static and dynamic obstacles. Motion planning algorithms generally plan over a future time horizon to smoothly follow the route and determine the car's optimal control (steering/acceleration). For planning through a future horizon, one requires the possible positions of all the relevant obstacles in future time-steps. Solutions for predicting an obstacle's future trajectory usually involve neural networks to perform sequence learning and generative algorithms to create multiple possibilities for a pedestrian's future state. This is done by attempting to learn the underlying distribution describing the obstacle motion. However, in practice, one cannot evaluate if this learnt distribution is accurate. This thesis addresses this issue by introducing a fully data-based alternative for trajectory prediction called the Partitioned Experience Method (PEM), which predicts future trajectories based solely on previously recorded data. In this way, it is not necessary to explicitly learn the underlying distribution of the pedestrian motion. The implemented trajectory prediction is validated using two metrics, recall and variance, introduced in this work. The trajectory prediction is also evaluated using a state-of-the-art motion planning algorithm. The results obtained from the motion planner indicate that using the PEM reduces the number of collisions and close contacts with other road users, and the corresponding trajectory followed by the car is closer to the reference trajectory.

Research and development of motion control in the field of autonomous driving is significantly increasing nowadays. Model predictive control (MPC) is one of the most powerful and practical tools currently available. It is important to select the parameters of the MPC, such as weights, in a way so that different control objectives can be met within the desired performance constraints. The tuning procedure of the MPC variables can be achieved automatically by employing appropriate approaches. To make the tuning process more robust to different scenarios, one approach is to choose a decision-making architecture that provides guidance. This thesis therefore aims at developing a system integrating an automatic tuning method with a decision-making module. In order to achieve the objectives, Genetic Algorithm and Behavior Tree are employed on top of an existing motion planner. The motion planner is based on model predictive contouring control (MPCC) and the proposed method is tested in CARLA simulation environment. This report also highlights the limitations of the proposed automatic tuning method and gives concrete recommendations on how to deal with the shortcomings.

Nonholonomic mechanical systems encompass a large class of practically interesting robotic structures, such as wheeled mobile robots, space manipulators, and multi-fingered robot hands. However, few results exist on the cooperative control of such systems in a generic, distributed approach. In this work we extend a recently developed distributed \ac{IDA-PBC} method to such systems. More specifically, relying on port-Hamiltonian system modelling for networks of mechanical systems, we propose a full-state stabilization control law for a class of nonholonomic systems within the framework of distributed \ac{IDA-PBC}. This enables the cooperative control of heterogeneous, underactuated and nonholonomic systems with a unified control law. This control law primarily relies on the notion of Passive Configuration Decomposition and a novel, non-smooth control law proposed here. A low-level collision avoidance protocol based on the \ac{APF} method is also implemented in order to achieve dynamic inter-agent collision avoidance, enhancing the practical relevance of this work. Theoretical results are tested in different simulation scenarios in order to highlight the applicability of the derived method.