Robot hand throws multiple objects faster and more accurately
Fast Planning for Multi-object Multi-target Throwing
Robotics
Summary
Throwing objects using robots can help speed up tasks like packing or sorting items. The authors developed a way for a robot hand to throw many objects to different places in a single movement, rather than throwing each one separately. They created a fast method to plan these throws, balancing how quickly the robot moves with how fast the plans can be made. Their tests showed this method can almost double the speed compared to throwing objects one at a time, and the robot can even adjust if the targets change while it is throwing. This work shows a new way for robots to handle multiple items quickly and flexibly.
What this means in practice
- •For warehouse automation teams: Deploy robots that can efficiently throw multiple items simultaneously to improve sorting and packing throughput.
- •For industrial robot integrators: Integrate fast planning methods for multi-object throws into existing robotic arms handling logistics tasks to reduce cycle time.
Authors
Zhengming Zhu, Yang Liu, Xiao Gao, Aude Billard
Abstract
Robot throwing has emerged as a promising technique for improving efficiency in logistics and warehouse automation, by enlarging the workspace and speeding up the process. To significantly increase the throwing system's throughput, we develop strategies for throwing multiple objects in one swipe. Such multi-object multi-target throwing (MOMT) leverages the large degrees of freedom of anthropomorphic hands. The key is to quickly generate fast and feasible throwing motions, which involves a complex trade-off between short trajectory duration and short planning time. We solve this problem in two stages. Offline, we build a model of the feasible set by combining object's inverted flying dynamics and the robot's kinematics and dynamics. Online, we generate feasible throws through fast solution matching and filtering of object's valid detach state and robot's feasible state that can compose sequences of throws in less than 5 ms. We validate the framework on a 7-DoF manipulator equipped with a multi-fingered hand. In simulation, coordinated two-object throwing reduces execution time by up to 46% compared to independent single-object planning, and this improvement is maintained when scaling to three objects. Real-world experiments with two objects confirm a 29% reduction; the remaining gap to the theoretical 50% is attributed to inter-throw transition overhead. When target positions are randomly changed mid-execution, the system re-plans and successfully reaches the new targets within 100 ms latency without stopping the robot. These results establish the first unified planning framework for MOMT throwing -- demonstrating scalability to multiple objects in simulation and real-world feasibility on two-object tasks -- advancing the frontier of high-throughput robotic manipulation. A video summarizing the method and the hardware experiments is available at https://liuyangdh.github.io/momt-video