Publications

Conference Papers

Design and Adaptive Depth Control of a Micro Diving Agent

Published in IEEE Robotics and Automation Letters (RA-L), 2017

This letter presents the depth control of an autonomous micro diving agent called autonomous diving agent (ADA). ADA consists of off-the-shelf components and features open-source hardware and firmware. It can be deployed as a testbed for depth controllers, as well as a mobile sensor platform for research or in industrial tanks. We introduce a control law that is based on the feedback linearization method and enhanced by an adaptive fuzzy algorithm to cope with modeling inaccuracies. The proposed depth controller is computationally light enough to run on ADAs embedded hardware. In experiments performed in a wave tank, the adaptive fuzzy scheme shows the ability to deal with both depth regulation and depth profile tracking. ADA is even able to hold on to dynamic isobars despite external disturbances. We demonstrate that under the influence of waves, ADA describes orbital motions similar to water particles.

Recommended citation: W. M. Bessa, E. Kreuzer, J. Lange, M. Pick and E. Solowjow, "Design and Adaptive Depth Control of a Micro Diving Agent", in IEEE Robotics and Automation Letters, vol. 2, no. 4, pp. 1871-1877, Oct. 2017, doi: 10.1109/LRA.2017.2714142. http://doi.org/10.1109/LRA.2017.2714142

Academic

Comparing popular simulation environments in the scope of robotics and reinforcement learning

Published in arXiv.org, 2021

This letter compares the performance of four different, popular simulation environments for robotics and reinforcement learning (RL) through a series of benchmarks. The benchmarked scenarios are designed carefully with current industrial applications in mind. Given the need to run simulations as fast as possible to reduce the real-world training time of the RL agents, the comparison includes not only different simulation environments but also different hardware configurations, ranging from an entry-level notebook up to a dual CPU high performance server. We show that the chosen simulation environments benefit the most from single core performance. Yet, using a multi core system, multiple simulations could be run in parallel to increase the performance.

Recommended citation: M. Körber, J. Lange, S. Rediske, S. Steinmann, R. Glück, "Comparing popular simulation environments in the scope of robotics and reinforcement learning", in arXiv preprint, March 2021, eprint: 2103.04616. https://arxiv.org/abs/2103.04616

Obstacle avoidance-driven controller for safety-critical aerial robots

Published in Hamburg University of Technology (TUHH), 2019

The goal of this thesis is to propose the combination of Control-Barrier-Functions (CBF) with Model-Predictive-Control (MPC) resulting in the novel Model-Predictive-Control-Barrier-Function (MPCBF). It can be shown, that the performance of the MPCBF surpasses the performance of the CBF due to the increased time horizon of the MPC. Moreover, the MPCBF was applied to a quadrotor, a system strongly in need of fast and predictive control. Using the MPCBF, the quadrotor was able to avoid obstacles, which the CBF failed to avoid due to the relative speed of the obstacle. The results of this work are experimentally validated.

Recommended citation: J. Lange, "Obstacle avoidance-driven controller for safety-critical aerial robots", in Hamburg University of Technology (TUHH), Sep. 2019, eprint: 2011.08178. https://arxiv.org/abs/2011.08178