Semantic Mapping, Navigation, and Obstacle Avoidance for the Autonomous PlatformPURPOSE OF THE STUDYTo increase the knowledge and expertise within the evolving automotive industry, Infotiv Technology Development AB developed the open and educational Autonomous Platform. It is currently in its fourth iteration (AP4) and the goal of the platform is to have an autonomous go-kart that can be used to progress research and development in the automotive industry. The purpose of the study is to design and implement a full perception-to-navigation pipeline on the AP, combining simultaneous localisation and mapping (SLAM) with multi-sensor fusion, semantic object detection, and intelligent path planning. Rather than relying on pre-built maps or reactive obstacle avoidance alone, the platform should be capable of incrementally building a map, populating it with detected objects, and exploiting visual landmarks to plan paths that are both safe and contextually aware. The goal is to evaluate and improve the effectiveness of the Autonomous Platform for one or several of the items below:Building and maintaining an accurate map of the environment using SLAM with fused data from LiDAR, camera, IMU or LaserDetecting, classifying, and localising objects in the environment and storing them as semantic annotations within the mapUsing visual cues, such as lane markings, signage, and recognisable landmarks , to improve localisation accuracy and path selectionPlanning routes that account for both static map knowledge and dynamically detected obstaclesValidating the full system on the physical AP hardware and inside the existing simulation environmentPOTENTIAL RESEARCH QUESTIONSHow does fusing LiDAR with camera data and other sensors affect SLAM accuracy and map completeness compared to single-…

Master thesis proposal