Event
Peking University team proposes hybrid model for flexible arm motion prediction
1 reports · 1 sources
The team of Xie Guangming and Zhang Feitian at Peking University proposed a hybrid prediction model to suppress error accumulation in step-by-step prediction for flexible robotic arms; the results were published at RSS 2026. The model consists of a balanced anchoring model and a lightweight correction model. On a simulated 3D cable-driven robotic arm, the team had the model predict 200 steps (6 seconds) of motion beyond the training range; the hybrid model's error was reduced by more than one quarter compared with using the anchoring model alone, and all 19 tests remained accurate. On a physical hydraulic soft robotic fish tail, its error was half or less that of the anchoring model and one quarter or less that of the correction model. The team states that more stable prediction can allow the controller to first simulate multiple actions in the computer and select the safest one.
Report timeline
- Peking University team proposes motion prediction method for flexible robotic arms, reducing long-range error by more than a quarter
A team led by Xie Guangming and Zhang Feitian at Peking University proposed a hybrid model that uses an equilibrium anchoring model and a lightweight correction model to suppress the accumulation of step-by-step prediction errors in flexible robotic arms. The work was published at RSS 2026. When predicting 200 steps (6 seconds) on a simulated 3D cable-driven robotic arm, the hybrid model's error was more than a quarter lower than that of the anchoring model alone, and none of 19 tests showed loss of accuracy. On a physical hydraulic soft robotic fish tail, its error was half or less that of the anchoring model and a quarter or less that of the correction model. More stable predictions could let a controller first try out multiple actions in a computer and pick the safest one.
Tech Xplore Robotics ·