Synthesis of the probabilistic collision avoidance system in the domain of dynamic objects motion

Anton Dotsenko

Abstract


The article is devoted to the control system synthesis problem considering collision avoidance system in the task of collective regrouping of dynamic objects. Our goal is to find the closed loop control system with probabilistic mapping of the current state vector to the optimal control vector. We propose to consider the control of pairs of dynamic objects, as simultaneous collision of more than 2 multiple objects can be decomposed to build a set of individual pairs of objects for which the violation of phase dynamic constraints is taking place. Control system is realized as a conditional density function with control as a random variable conditioned on the states of both dynamic object and moving obstacle, which reflects the novelty of the research. Proposed control system is universal in a sense that it is able to resolve collisions between dynamic objects even in the unknown environment for arbitrary initial and terminal states given for objects. Moreover, it is able to consider alternate obstacle avoidance routes through the probability density function of control. The control system also assumes the control of the group is decentralized. Individual object will be acting as a standalone system after the control system is uploaded in the memory.

Full Text:

PDF (Russian)

References


Barraquand J., Latombe J. C. Robot motion planning: A distributed representation approach // The International Journal of Robotics Research. – 1991. – Vol. 10, no. 6. – P. 628–649.

LaValle S. M. Planning algorithms / – Cambridge university press, 2006. – 842 p.

Kapadia M., Singh S., Hewlett W., Reinman G., Faloutsos, P. Parallelized egocentric fields for autonomous navigation // The Visual Computer. – 2012. – Vol. 28, no. 12. – P. 1209–1227.

Park J. W., Kwak H. J., Kang Y. C., Kim D. W. Advanced fuzzy potential field method for mobile robot obstacle avoidance / // Computational intelligence and neuroscience. – 2016. – Vol. 2016.

O’Donnell P. A., Lozano-Pérez T. Deadlock-free and collision-free coordination of two robot manipulators // ICRA. Vol. 89. – 1989. – P. 484–489.

Jansen M. R., Sturtevant N. R. Direction Maps for Cooperative Pathfinding. // AIIDE. – 2008. – Vol. 2008. – P. 185.

Hennes D. et al. Multi-robot collision avoidance with localization uncertainty // AAMAS. – 2012. – P. 147–154.

Alejo D., Cobano J. A. Heredia G. Reactive method for collision avoidance in industrial environments // Journal of Intelligent & Robotic Systems. – 2016. – Vol. 84, no. 1–4. – P. 745–758

Diveev A. I., Shmalko E. Y. Self-adjusting control for multi robot team by the network operator method // 2015 European Control Conference (ECC). – IEEE. 2015. – P. 709–714.

Diveev A. I., Shmalko E. Y. Optimal motion control for multi-robot system by multilayer network operator // 2016 IEEE 11th Conference on Industrial Electronics and Applications (ICIEA). – IEEE. 2016. – P. 2164–2169.

Diveev A., Shmalko E. Hybrid evolutionary algorithm for synthesized optimal control problem for group of interacting robots // 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT). – IEEE. 2019. – P. 876–881.

Diveev, A., Hussein, O., Shmalko, E., Sofronova, E. Synthesis of Control System for Quad-Rotor Helicopter by the Network Operator Method // Proceedings of SAI Intelligent Systems Conference. –– Springer. 2020. – P. 246–263.

Diveev. A. Cartesian Genetic Programming for Synthesis of Control System for Group of Robots // 2020 28th Mediterranean Conference on Control and Automation (MED). – IEEE. 2020. – P. 972–977.

Dubovitskiy A. Y., Milyutin A. A. Extremum problems in the presence of constraints // Journal of numerical mathematics and mathematical physics. – 1965. – Vol. 5, no. 3. – С. 395–453.

Dotsenko A. V. Automatic synthesis of a continuous dynamic stabilization system based on artificial neural networks// Herald of the Bauman Moscow state technical university, Instrument Ingineering. – 2020. – no.3. – С. 66-83.

Bishop C. M. Mixture density networks. – 1994.

Wang M., Lu S., Zhu D., Lin J., Wang Z. A high-speed and low-complexity architecture for softmax function in deep learning //2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS). – IEEE, 2018. – С. 223–226.

Salimans T., Ho J., Chen X., Sidor S., Sutskever I. Evolution strategies as a scalable alternative to reinforcement learning // arXiv preprint arXiv:1703.03864. – 2017.

Wierstra D. et al. Natural evolution strategies // The Journal of Machine Learning Research. – 2014. – Vol. 15, no. 1. – P. 949–980.

Dubins L. E. On curves of minimal length with a constraint on average curvature and with prescribed initial and terminal positions and tangents // Amer. J. Math., 1957, Vol. 79. P. 497-516.


Refbacks

  • There are currently no refbacks.


Abava  Absolutech Convergent 2020

ISSN: 2307-8162