Background: Requirements engineering (RE) is the process of identifying, defining, documenting, and validating requirements. However, RE approaches are usually not applied to AI-based systems due to their ambiguity and is still a growing subject. Research also shows that the quality of ML-based systems is affected due to the lack of a structured RE process. Hence, there is a need to apply RE techniques in the development of ML-based systems.  Objectives: This research aims to identify the practices and challenges concerning RE techniques for AI-based systems in autonomous driving and then to identify a suitable RE approach to overcome the identified challenges. Further, the thesis aims to check the feasibility of the selected RE approach in developing a prototype AI-based classification system for road markings.  Methods: A combination of research methods has been used for this research. We apply techniques of interviews, case study, and a rapid literature review. The case company is Scania CV AB. A literature review is conducted to identify the possible RE approaches that can overcome the challenges identified through interviews and discussions with the stakeholders. A suitable RE approach, GR4ML, is found and used to develop and validate an AI-based classification system for road markings.  Results: Results indicate that RE is a challenging subject in autonomous driving. Several challenges are faced at the case company in eliciting, specifying, and validating requirements for AI-based systems, especially in autonomous driving. Results also show that the views in the GR4ML framework were suitable for the specification of system requirements and addressed most challenges identified at the case company. The iterative goal-oriented approach maintained flexibility during development. Through the system's development, it was identified that the Random Forest Classifier outperformed the Logistic Regressor and Support Vector Machine for the road markings classification.  Conclusions: The validation of the system suggests that the goal-oriented requirements engineering approach and the GR4ML framework addressed most challenges identified in eliciting, specifying, and validating requirements for AI-based systems at the case company. The views in the GR4ML framework provide a good overview of the functional and non-functional requirements of the lower-level systems in autonomous driving. However, the GR4ML framework might not be suitable for validation of higher-level AI-based systems in autonomous driving due to their complexity.

Utilization of additional information of the pulse for ALS data classification in ragged terrain Abstract The diploma thesis deals with airborne laser scanning filtering problem in sandstone landscape which is characterized by ragged terrain and in our country also by dense vegetation that makes difficult to transit laser pulse to terrain that can lead to lower accuracy of created DTM. In the first part the basic filtering algorithm that are systematic divided into several groups are described. The emphasis is also put on theoretic problems which we have to deal with during the filtering of laser scanner data acquired in sandstone landscape. The main goal of the thesis is to suggest changes in one of the existing algorithm to additional information of the pulse (mainly amplitude and width of the pulse) be used, and to test this method over the real data. At the end the results of the method and its implementation are critically evaluated. Keywords: airborne laser scanning, point cloud segmentation, point cloud classification, sandstone landscape, DTM

The importance of single-tree-based information for forest management and related industries in countries like Sweden, which is covered in approximately 65% by forest, is the motivation for developing algorithms for tree detection and species identification in this study. Most of the previous studies in this field are carried out based on aerial and spectral images and less attention has been paid on detecting trees and identifying their species using laser points and clustering methods. In the first part of this study, two main approaches of clustering (hierarchical and K-means) are compared qualitatively in detecting 3-D ALS points that pertain to individual tree clusters. Further tests are performed on test sites using the supervised k-means algorithm in which the initial clustering points are defined as seed points. These points, which represent the top point of each tree are detected from the cross section analysis of the test area. Comparing those three methods (hierarchical, ordinary K-means and supervised K-means), the supervised K-means approach shows the best result for clustering single tree points. An average accuracy of 90% is achieved in detecting trees. Comparing the result of the thesis algorithms with results from the DPM software, developed by the Visimind Company for analysing LiDAR data, shows more than 85% match in detecting trees. Identification of trees is the second issue of this thesis work. For this analysis, 118 trees are extracted as reference trees with three species of spruce, pine and birch, which are the dominating species in Swedish forests. Totally six methods, including best fitted 3-D shapes (cone, sphere and cylinder) based on least squares method, point density, hull ratio and slope changes of tree outer surface are developed for identifying those species. The methods are applied on all extracted reference trees individually. For aggregating the results of all those methods, a fuzzy logic system is used because of its good reputation in combining fuzzy sets with no distinct boundaries. The best-obtained model from the fuzzy system provides 73%, 87% and 71% accuracies in identifying the birch, spruce and pine trees, respectively. The overall obtained accuracy in species categorization of trees is 77%, and this percentage is increased dealing with only coniferous and deciduous types classification. Classifying spruce and pine as coniferous versus birch as deciduous species, yielded to 84% accuracy.

A fundamental aspect to consider in factories is the transportation of the items at differentsteps in the production process. Conveyor belts do a great to bring items from point A topoint B but to load the item onto a working station it can demands a more precise and,in some cases, delicate approach. Nowadays this part is mostly handled by robotic arms.The issue encountered is that a robot arm extremity, its gripper, cannot directly instinctivelyknow how to grip an object. It is usually up to a technician to configure how andwhere the gripper goes to grip an item.The goal of this thesis is to analyse a problem given by a company which is to find a wayto automate the grasp pose synthesis of a new object with the adapted gripper.This automatized process can be separated into two sub-problems.First, how to choose the adapted gripper for a new object.Second, how to find a grasp pose on the object, with the previously chosen gripper.In the problem given by the company, the computer-aided design (CAD) 3D model of theconcerned object is given. Also, the grasp shall always be done vertically, i.e., the grippercomes vertically to the object and the gripper does not rotate on the x and y axis. Thegripper for a new object is selected between two kinds of grippers: two-finger paralleljawgripper and three-finger parallel-jaw gripper. No dataset of objects is provided.Object grasping is a well researched subject, especially for 2 finger grippers. However,few research is done for the 3 finger grippers grasp pose synthesis, or for gripper comparison,which are key part of the studied problem.To answer the sub-problems mentioned above, machine learning will be used for the gripperselection and a grasp synthesis method will be used for the grasp pose finding. However,due to the lack of gripper comparison in the related work, a new approach needsto be created, which will be inspired by the findings in the literature about grasp posesynthesis in general.This approach will consist of two parts.First, for each gripper and each object combination are generated some grasp poses, eachassociated with a corresponding score. The scores are used to have an idea of the bestgripper for an object, the best score for each gripper indicating how good a grasp couldbe on the object with said gripper.Secondly, the objects with their associated best score for each gripper will be used astraining data for a machine learning algorithm that will assist in the choice of the gripper.This approach leads to two research questions:“How to generate grasps of satisfying quality for an object with a certain gripper?”“Is it possible to determine the best gripper for a new object via machine learning ?”The first question is answered by using mathematical operations on the point cloud representationof the objects, and a cost function (that will be used to attribute a score), whileithe second question is answered using machine learning classification and regression togain insight on how machine learning can learn to associate object proprieties to gripperefficiency.The found results show that the grasp generation with the chosen cost function givesgrasp poses that are similar to the grasp poses a human operator would choose, but themachine learning models seem unable to assess grasp quality, either with regression orclassification.