Spreading excellence and disseminating the cutting edge results of our research and development efforts is crucial to our institute. Check for our educational offers for Bachelor, Master and PhD studies at the University of Innsbruck!

Improving decision making in autonomous vehicles with semantics-enhanced object detection

Type: 
Master

Autonomous vehicles (AV) which are thought of as the future of mobility are now becoming reality. The sensors such as RADAR, LiDAR, camera which form the sensing unit are the foundations of AV. The input from the sensing units are used for perception tasks such as localization, detection, predictions, which then is  used for making decisions in AVs for navigation. The perception task, objection detection, is a key to the safety in AV. 

However, due to numerous factors, the input from the sensors are not always of sufficient quality; for example, missing data frames, sparse data. The quality of data directly affects the perception task, particularly object detection and thus the quality of decision making which relies on outcome of perception. Improving the object detection result, accuracy, we can improve the decision making in AV. Semantic technology, namely ontology and knowledge graphs, which have the capability of maintaining relationships, can be used to enrich the data, provide interoperability, represent the problems like in the real-world due to its graph structure. The objective of this thesis is to use semantic technology to improve the decision making by improving the quality of object detection together with deep learning. 

Technology Stack: Python, Robot Operating System, Semantic Technology (Knowledge Graph, Ontology), Linux, Deep Learning, LGSVL simulator

References:

  1. Jia, M., Shi, M., Sirotenko, M., Cui, Y., Hariharan, B., Cardie, C. and Belongie, S., 2019. The fashionpedia ontology and fashion segmentation dataset. Cornell University.
  2. Kharlamov, E., Brandt, S., Jimenez-Ruiz, E., Kotidis, Y., Lamparter, S., Mailis, T., Neuenstadt, C., Özçep, Ö., Pinkel, C., Svingos, C. and Zheleznyakov, D., 2016, June. Ontology-based integration of streaming and static relational data with optique. In Proceedings of the 2016 International Conference on Management of Data (pp. 2109-2112).
  3. Fang, W., Ma, L., Love, P.E., Luo, H., Ding, L. and Zhou, A., 2020. Knowledge graph for identifying hazards on construction sites: Integrating computer vision with ontology. Automation in Construction119, p.103310.
  4. Liu, B., Yao, L., Ding, Z., Xu, J. and Wu, J., 2018. Combining ontology and reinforcement learning for zero-shot classification. Knowledge-Based Systems144, pp.42-50.
  5. https://www.ros.org
  6. https://www.lgsvlsimulator.com 
  7. Huang, L., Liang, H., Yu, B., Li, B. and Zhu, H., 2019, July. Ontology-Based Driving Scene Modeling, Situation Assessment and Decision Making for Autonomous Vehicles. In 2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) (pp. 57-62). IEEE.
  8. Iskra, N., Iskra, V. and Lukashevich, M., 2019. Neural network based image understanding with ontological approach.

We are hiring!

Check out our researcher job positions at https://www.sti-innsbruck.at/about/jobs