Authors: Zeev Yampolsky, Felipe O. Silva, Adriano Frutuoso, Itzik Klein
Organizations: The Hatter Department of Marine Technologies, Charney School of Marine Sciences, University of Haifa, Haifa, Israel · Department of Automatics, School of Engineering Federal University of Lavras, Lavras, MG, 37200-900, Brazil · Department of Higher Education Federal Institute of Amazonas, Manaus, AM, 69075-351, Brazil
Autonomous platforms operating in the oceans require accurate navigation to successfully complete their mission. In this regard, the initial heading estimation accuracy and the time required to achieve it play a critical role. The initial heading is traditionally estimated by model-based approaches employing orientation decomposition. However, methods such as the dual vector decomposition and optimized attitude decomposition achieve satisfactory heading accuracy only after long alignment times. To allow rapid and accurate initial heading estimation, we propose an end-to-end, model-free, neural-assisted framework using the same inputs as the model-based approaches. Our proposed approach was trained and evaluated on real-world dataset captured by an autonomous surface vehicle. Our approach shows a significant accuracy improvement over the model-based approaches achieving an average absolute error improvement of 53%. Additionally, our proposed approach was able to reduce the alignment time by up to 67%. Thus, by employing our proposed approach, the reduction in alignment time and improved accuracy allow for a shorter deployment time of an autonomous platform and increased navigation accuracy during the mission.
Fig. 2 : Detailed block diagram showing the proposed neural-assisted in-motion self-heading alignment architecture, that is HeadingNet, and the possible variation due to TAlign variations.
Fig. 3 : Illustration of an average pooling operation with a kernel of size k , applied over a T second measurement window containing n IMU measurements and m transport-rate and gravity measurements, where n>m .
Fig. 4 : Data flow diagram of starting from the raw measurements from the ASV sensors, the IMU and GNSS-RTK, to our proposed approach HeadingNet.
Fig. 5 : Heading angles plot of the first 350 seconds for the five recorded trajectories, R1 to R5.
Fig. 6 : Heading angles plot of the four evaluation recordings, EvalR1 to EvalR4.
Fig. 7 : Block diagram illustrating the data preparation pipeline to generate the training sets and datasets and evaluation set to train and evaluation all HeadingNet variations.
Fig. 8 : AE Results of the heading estimation in degrees for the four evaluation recordings, EvalR1 to EvalR4, at the examined alignment time periods, for HeadingNet and the four baseline methods.
Fig. 9 : Average AE heading in degrees results of all baseline methods and HeadingNet variations. The black dashed line represents the heading AE of HeadingNet10, and the red dashed line represents the HeadingNet30 results, thus the proposed approach HeadingNet result at these two alignment times.
Fig. 10 : AE improvement bar plot in percentage showing our proposed the improvement of our proposed HeadingNet over the best baseline method.
Computer Vision Laboratory, Department of Electrical Engineering, Linköping University, Sweden · Inception Institute of Artificial Intelligence, Abu Dhabi, UAE