We excited to share that IAAC annual meeting of graduate students in Systems and Control was held for the first time at the University of Haifa and was a great success.

It was organized  by our own Prof. Itzik Klein and featured talks from two of our PhD students:

Daniel Engelsman, Towards Learning-Based Gyrocompassing.

Dan Solodar, VIO-DualProNet: Visual-Inertial Odometry with Learning Based Process Noise Covariance.

In addition, three of our students: Nadav Cohen, Aviad Etzion, and Zeev Yampolsky chaired the sessions during the conference.

Yair Stolero presented his research on reducing low-cost gyroscope calibration time by employing deep learning methods and multiple IMUs

Prof. Klein was honored to chair the session focused on deep-learning navigation for autonomous underwater vehicles. ANSFL three Ph.D. students took center stage and share their research with the world. Their presentations were met with enthusiastic questions and sparked some fascinating discussions. 

Nadav Cohen talked on our data-driven strategies for coping with incomplete Doppler velocity log measurements to allow seamless autonomous underwater vehicle navigation.

Zeev Yampolsky addressed Doppler velocity log calibration using our proposed data-driven methods, which allow more accurate and fast calibration process.

Daniel Engelsman introduced a dedicated learning framework aimed at mitigating environmental effects and offering precise underwater gyrocompassing.

Prof. Klein joins the leadership team of DSRC, the Data Science Research Center at the University of Haifa! 

Registration link: 

https://docs.google.com/forms/d/e/1FAIpQLSdDgdcY9KhY3-wxyIVda7tNJtjoc0BRCbnlGkTkl1nH11D6DQ/viewform

Collection Link: 

https://link.springer.com/collections/bffibjceih

Editors: Prof. Oren Gal and Prof. Itzik Klein

Scope: Data science has become a vital element in autonomy and navigation, improving decision-making processes and providing accurate navigation capabilities. Additionally, sensory data collected from diverse sensors is a counterstone in developing sophisticated sensor fusion algorithms using deep learning or hybrid methodologies. Advances in real-time processing facilitate faster decision making and obstacle avoidance for autonomous systems that can be operated in very limited hardware computation capacity. Data science continues to be a driving force in autonomy and navigation. It provides the tools and techniques to address these challenges and push the boundaries of what autonomous systems can achieve. This Topical Collection aims at collecting high quality research papers and review articles focusing on recent advances in data-driven based autonomy and navigation.

Registration link: 

https://docs.google.com/forms/d/e/1FAIpQLSdDgdcY9KhY3-wxyIVda7tNJtjoc0BRCbnlGkTkl1nH11D6DQ/viewform