Learning to Control the Whole-Body Shape of a Soft Robotic Arm in Unknown Situations
Zhiqiang Tang, Qianqian WANG, Daniela Rus, Cecilia Laschi
AI summary
Problem
Most existing soft robot control methods focus only on end-effectors or partial segments, leaving whole-body shape control underexplored despite its necessity for navigating confined spaces and adapting to unpredictable environments.
Approach
The authors train an offline CNN policy to generate baseline actions, then use an image-based shape model updated in real time alongside Bayesian optimization to iteratively refine control actions and adapt to unknown conditions.
Key results
- Achieved over 90% shape matching accuracy across diverse target configurations
- Successfully adapted to unknown tip loads, distributed body weights, and external wind disturbances
- Outperformed state-of-the-art inverse kinematic methods in both accuracy and adaptive robustness
- Enabled real-time online model updating and efficient Bayesian action optimization
Why it matters
Provides a practical, adaptive control framework that expands the operational versatility of soft robots in unstructured and dynamic environments.
Abstract
Control of soft robots is considered one of the key elements in achieving their intelligence. However, it faces challenging problems such as nonlinear dynamics, highly de- formable structures, and operation in unpredictable situations. Numerous methods have been proposed to overcome these challenges, but most of them focus on controlling only a small part of the soft robot’s body, such as the end effector. Whole- body shape control is a problem that has not yet been fully explored, but it is critical for tasks that require whole-body path planning to navigate in confined or crowded spaces. In this study, we developed a convolutional neural network (CNN)- based approach for controlling the robot’s whole-body shape. The key novelty of our approach is that it learns a purely image- driven CNN control policy with online adaptive capability. Our approach has three main components: (1) training an offline shape policy to offer basic actions, (2) building a shape model and updating it online to maintain accuracy, (3) conducting Bayesian optimization based on the basic action and shape model to obtain optimal performance. The presented approach is validated on a soft robotic arm and experimental results demonstrate that the soft arm can be controlled to achieve target shapes and adapt to different previously unknown situ- ations. Meanwhile, our approach achieved better shape control performance than the state-of-the-art method. Overall, this work presents a feasible learning-based approach to the whole- body shape control problem and contributes to the development of soft robot intelligence from the control perspective.