3D OBJECT DETECTION AND TRAJECTORY PREDICTION FOR AUTONOMOUS VEHICLES

Background of thesis project


Volvo Construction Equipment (VCE) is one of the world's largest manufacturers of construction equipment. With enhancing the artificial intelligent area and learning-based approaches, there is a big trend for shifting towards autonomous vehicles which can localize themselves in the environment, perceive and plan. In the construction domain, object detection is an essential mean to enable autonomous driving where machines can detect objects, track them, and forecast their future trajectories. To maintain a leading position, it is essential for Volvo to develop innovative and cost-efficient and high-performance solutions for object detection and trajectory forecasting.


Suitable background


This master thesis is suitable for one student that is completing their studies in computer science. The thesis will be lead by Volvo Construction Equipment. Desired start date is Jan 2023.

Description of thesis work


Prior studies [1, 2] tried to solve the problem of joint object detection and trajectory forecasting, however, they suffer from inefficient implementation and/or being customized for on-road environments. This project aims to design and train an efficient deep neural network (DNN) for detecting objects and forecasting the future trajectory of moving object using point cloud data in the environment of autonomous VOLVO construction vehicles.
The original dataset will be provided by VCE containing point cloud video frames obtained by the LiDAR sensor. The student is preferably knowledgeable in deep learning, and Python is meriting. The main activities are:
Reviewing related studies point cloud object detection and trajectory forecasting.
Preparing dataset (labeling, normalization, etc.) from raw LiDAR point cloud data provided by VOLVO.
Implementing a SoTA DNN model for object detection and trajectory forecasting
Train ithe model that has been prepared in Step 3 on the VOLVO dataset.
Evaluating accuracy and latency of the proposed DNN model.

A full report of the work carried out will be prepared and presented to staff at Volvo CE. It will be required for the student to perform the thesis at Volvo CE facilities in Eskilstuna.


References


[1] Zhang, Zhishuai, et al. "Stinet: Spatio-temporal-interactive network for pedestrian detection and trajectory prediction." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.
[2] Peri, Neehar, et al. "Forecasting from LiDAR via Future Object Detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.


Thesis Level: Master

Language: English


Starting date: January 2023


Number of students: One student


Tutor
Name, title, phone
Sara Afshar, Research Owner at Emerging Technology, +46 1654 15707
Mohammad Loni, Research Engineer at Emerging Technology, +46 165414570