Problem
Research questions and friction points this paper is trying to address.
soft growing robot
visuomotor control
hysteresis
deformation
autonomous navigation
PanoVine: Whole-Body Visuomotor Control for Soft Growing Vine Robot
🤖 AI Summary
Soft growing vine robots are challenging to model due to hysteresis, cable interference, and large deformations, which limit the effectiveness of traditional control methods in unstructured environments. This work proposes the first autonomous vine robot system based on whole-body distributed visual feedback, integrating 19 cameras along the robot’s body with data-driven, end-to-end visuomotor policy learning and imitation learning to close the perception–action loop. The approach overcomes longstanding autonomy bottlenecks for soft growing robots in complex settings, successfully accomplishing demanding tasks such as branch path selection, slope climbing, traversal of unsupported terrain, precise grasping, and obstacle avoidance in confined spaces. These capabilities significantly enhance the system’s robustness and generalization performance.
📝 Abstract
Vine robots, a class of soft, growing robots, are suitable for navigating complex and confined environments due to their compliant bodies and self-supporting growth mechanism. However, hysteresis, tether interactions, and deformations make them difficult to predict and model, which in turn limits the effectiveness of conventional planning and control approaches. In this work, we present a data-driven, vision-based control framework for the first autonomous vine robot system. Our system integrates 19 cameras distributed along the robot's body to provide comprehensive feedback of both the robot state and the surrounding environment. Using this rich whole-body vision feedback, we train an end-to-end visuomotor policy from demonstrations for closed-loop autonomous control in complex environments. The policy efficiently aggregates information from distributed sensing while maintaining robustness to inaccurate robot states and actuation. Experimental results demonstrate that the learned policy enables robust navigation and manipulation in challenging scenarios, including steering through branched structures, climbing up slopes, traversing unsupported terrain, reaching objects precisely, and maneuvering through confined spaces and obstacles. Project website https://panovine-bot.github.io
Innovation
Methods, ideas, or system contributions that make the work stand out.
soft growing robot
whole-body vision
visuomotor control
end-to-end learning
distributed sensing
🔎 Similar Papers
No similar papers found.
