Environment Design for Reliable Shared Autonomy with Probabilistic Guarantees
Robotics
Summary
The authors study how the way objects are arranged in a workspace affects how well a robot can understand what a human wants during shared autonomy tasks. They found that some layouts make it easier for the robot to guess the human's goal, especially when there is noisy or unclear input. By treating the arrangement of objects as a problem to optimize, they created layouts that improve the robot's accuracy in guessing goals. They tested this both in simulations and in a real system, showing that designing the workspace helps the robot and human work better together.
Authors
Yi-Shiuan Tung, Himanshu Gupta, Gyanig Kumar, Heyang Huang, Bradley Hayes, Alessandro Roncone
Abstract
Shared autonomy enables humans and robots to collaboratively perform tasks by combining human input with autonomous assistance. Most prior work focuses on improving intent inference under a fixed environment, overlooking how workspace design itself affects inference difficulty. We observe that the physical arrangement of objects directly influences the separability of candidate goals under noisy user inputs. We formulate workspace design as an optimization problem and derive a probabilistic correctness guarantee under a bounded noise model. Through simulation experiments across multiple tabletop scenarios, we show that optimized layouts improve goal inference reliability and reduce ambiguity compared to baseline arrangements. We further demonstrate a real-world shared autonomy system that integrates the proposed inference framework. This highlights the role of environment design as a complementary axis for improving shared autonomy systems.