Coordinated Control of a Group of Warehouse Cobots for Collaborative Cargo Transport over Various Surface Types

Motion planning for a group of mobile robots collaboratively transporting a load over non-uniform support surfaces is a challenging task. The core difficulty lies in simultaneously satisfying conflicting requirements: safe obstacle avoidance, maintaining group formation, minimizing travel time or path length, and adhering to dynamic constraints imposed by varying ground properties. This paper proposes a hybrid method that overcomes the fundamental limitations of existing approaches, such as the low computational speed of sampling-based methods (RRT*), the non-strict constraint satisfaction in reinforcement learning (RL), and the rigid smoothness requirements of classical optimal control methods. The key idea is to combine optimal control with machine learning, where a neural network model approximates the objective function — a more versatile approach compared to approximating system dynamics or environment models. Two training strategies are investigated: supervised learning for accurately reproducing an objective function and reinforcement learning (DDPG algorithm) for flexibly defining it via a reward function. Constraints, including acceleration limits dependent on the surface type, are defined analytically using a smoothed discrete space and bilinear interpolation. The optimization problem is solved using the high-performance solver FATROP, integrated with the CasADi automatic differentiation framework. Simulation results demonstrate that the proposed method outperforms a previous RRT*-based implementation, reducing trajectory computation time 58-fold and decreasing path traversal time by 20 %. The experiments also showed that reinforcement learning allows for flexibly redefining the optimization goal, finding a shorter path (8.9 m vs. 9.4 m) at the cost of a slight increase in travel time. The FATROP solver also proved to be 22 % faster than the traditional IPOPT. These results confirm the potential of the hybrid approach for multi-robot motion planning tasks, enabling the integration of complex nonlinear dependencies without a significant loss in performance.

1. Galyaev A. A., Lysenko P. V., Yakhno V. P. 2D Optimal Trajectory Planning Problem in Threat Environment for UUV with Non-Uniform Radiation Pattern, Sensors, 2021, vol. 21, no. 2, p. 396, DOI: 10.3390/s21020396.

2. Kutakhov V. P., Mescheryakov R. V. Group control of unmanned aerial vehicles: a generalized problem statement of applying artificial intelligence technologies, Control Sciences, 2022, iss. 1, pp. 55—60 (in Russian).

3. Webb D. J., van den Berg J. Kinodynamic RRT*: Asymptotically optimal motion planning for robots with linear dynamics, IEEE International Conference on Robotics and Automation, 2013, pp. 5054—5061, DOI: 10.1109/ICRA.2013.6631299.

4. Ermolov I. L., Lapin В. S. Distributed trajectory planning for a group of UGVs carrying a load considerting terrain properties, Mekhatronika, Avtomatizatsiya, Upravlenie, 2023, vol. 24, no. 6, pp. 327—334, DOI 10.17587/mau.24.327-334 (in Russian).

5. Wachter A., Biegler L. T. On the Implementation of a Primal-Dual Interior Point Filter Line Search Algorithm for Large-Scale Nonlinear Programming, Mathematical Programming, 2006, vol. 106, no. 1, pp. 25—57, available at: http://www.optimization-online.org/DB_HTML/2004/03/836.html.

6. Vanroye L., Sathya A., De Schutter J., Decre W. FATROP: А Fast Constrained Optimal Control Problem Solver for Robot Trajectory Optimization and Control, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023, pp. 10036—10043, DOI: 10.1109/IROS55552.2023.10342336, available at: https://arxiv.org/abs/2303.16746.

7. Salzmann T., Jon Arrizabalaga J., Joel Andersson J., Pavone M., Ryll M. Learning for CasADi: Data-driven Models in Numerical Optimization, Proceedings of Machine Learning Research, 2024, pp. 1—13, available at: https://arxiv.org/abs/2312.05873.

8. Alhaddad M., Mironov K., Staroverov A., Panov А. Neural Potential Field for Obstacle-Aware Local Motion Planning, IEEE International Conference on Robotics and Automation (ICRA), 2024, available at: https://arxiv.org/abs/2310.16362.

9. Bikram P., Ashutosh G., Mohitvishnu S. G., Addison J., Aayam K. S., Helei D., Jeremy D., Alan F. Learning Decentralized Multi-Biped Control for Payload Transport, 8th Annual Conference on Robot Learning, 2024, available at: https://arxiv.org/abs/2406.17279v2.

10. Kalyaev I. A., Gaiduk A. R., Kapustyan S. G. Models and algorithms of collective control in groups of robots, Moscow, Fizmatlit, 2009, 278 p. (in Russian).

11. Lillicrap T. P., Hunt J. J., Pritzel A., Heess N., Tom Erez T., Tassa Y., Silver D., Wierstra D. Continuous control with deep reinforcement learning, 2019, available at: https://arxiv.org/abs/1509.02971

12. Andersson J. A. E., Gillis J., Horn G., Rawlings J. B., Diehl M. CasADi: a software framework for nonlinear optimization and optimal control, Mathematical Programming Computation, 2019, no. 11, pp. 1—36, available at: https://doi.org/10.1007/s12532-018-0139-4

13. Paszke A., Gross S., Massa F., Lerer A., Bradbury J., Chanan G., Killeen T., Lin Z., Gimelshein N., Antiga L., Desmaison A., Köpf A., Yang E., DeVito Z., Raison M., Tejani A., Chilamkurthy S., Steiner B., Fang L., Bai J., Chintala S. PyTorch: An Imperative Style, High-Performance Deep Learning Library, 2019, available at: https://arxiv.org/abs/1912.01703.

14. Raffin A., Hill A., Gleave A., Kanervisto A., Ernestus M., Dormann N. Stable-baselines3: reliable reinforcement learning implementations, The Journal of Machine Learning Research, 2021, vol. 22, no. 1, pp. 12348—12355, available at: https://dl.acm.org/doi/abs/10.5555/3546258.3546526