Qualcomm FY25 Intern - Thesis Safety-Aware Motion Planning Göteborg 

Sweden, Gothenburg 

347779946

Arriver Software AB

Job Area:

Interns Group, Interns Group > Interim Intern

Field:Collision Avoidance feature development

This thesis investigates how to detect situations that pose an increased risk and define the best longitudinal and lateral paths ahead within a fixed horizon associated with the risks. This information can then be used by the planning system or the driver to take precautionary action to mitigate the risk. The main input for the functionality will be perception data in the form of objects originating from fusion of computer vision and radar, as well as road geometry detection from computer vision. Additional data such as object prediction, road signs, ego motion, and map data can be utilized. Ego vehicle's longitudinal and lateral path that has the lowest cost function is identified by evaluating all longitudinal actions (like acceleration and deceleration) as well as lateral maneuvers (such as staying in the current lane or changing to the left or right lane). The cost function should measure the collision risk within the given time. This involves considering the detected objects within this timeframe, including prediction, and assessing the probability of their movements, even those that are occluded.

Using the predicted stochastic environment and an ego vehicle model, cost function could be evaluated within the horizon.

The main output will be limitation in allowed driving speed and lateral motion by designing a controller (steering, braking, warning). The thesis will contain the following: - Perform literature study on which methods are suitable to solve the problem. - Define traffic scenarios that are most relevant for the analysis. - Implement the selected strategy. - Evaluate how well the method can detect hazardous situations, from simulated and real-world data. - Evaluate if possible precautionary driving limits can reduce future risks if followed.

Learning objectives:Throughout the work the student(s) will learn how to apply theoretical knowledge on a real-world problem and get a broader understanding of the challenges faced when developing ADAS features today.

*References to a particular number of years experience are for indicative purposes only. Applications from candidates with equivalent experience will be considered, provided that the candidate can demonstrate an ability to fulfill the principal duties of the role and possesses the required competencies.

Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.