Research on robot path tracking method based on IDDPG-MPC
Haicheng Shen, Xun Xu, Zhiqiang Miao · 2026
Read Research on robot path tracking method based on IDDPG-MPC by Haicheng Shen, Xun Xu, Zhiqiang Miao (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0350307.txt.
Description
Haicheng Shen, Xun Xu, and Zhiqiang Miao present this 2026 PLOS One control-engineering paper on steering unmanned surface vessels along a set path in rough marine conditions. Traditional guidance methods lose accuracy when waves, currents, and the vessel's own quirks interfere. Their design stacks two layers: a reinforcement learning module that learns the environment and issues heading commands, and a predictive controller that turns those commands into thrust and rudder settings.
In simulations the hybrid system tracked its path far more tightly than a standard guidance-and-PID setup, cutting sideways drift by more than a third and heading error by about a fifth. Training tricks including gradient pruning and a custom reward kept learning stable. The authors offer the scheme as a step toward dependable autonomous boats.
Catalog record
| CREATOR | Haicheng Shen, Xun Xu, Zhiqiang Miao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68386 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |