The field of robotics is moving towards the development of systems that can effectively manipulate deformable objects, which poses significant challenges due to their complex dynamics and the need for safe interaction in contact-rich environments. Recent innovations have focused on creating hybrid approaches that combine learning and model-based optimization to estimate contact interactions and predict object behavior. Notably, researchers are exploring the use of deformable tools, soft robotic arms, and predictive control algorithms to achieve dexterous manipulation and safely interact with deformable linear objects.

These advancements have the potential to greatly improve the adaptability and safety of robotic systems in unstructured environments.

Some noteworthy papers in this area include:

• Estimating Deformable-Rigid Contact Interactions for a Deformable Tool via Learning and Model-Based Optimization, which proposes a hybrid approach to modeling simultaneous motion and force transfer of tools and objects.
• UMArm: Untethered, Modular, Wearable, Soft Pneumatic Arm, presents a novel pneumatically driven rigid-soft hybrid arm that achieves full untethered operation and high payload capacity.
• Certifiably Safe Manipulation of Deformable Linear Objects via Joint Shape and Tension Prediction, introduces a certifiably safe motion planning and control framework for DLO manipulation that integrates a predictive model with real-time trajectory optimization.
• Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control, proposes a novel framework for elasto-plastic object manipulation using 3D occupancy representation, learned dynamics models, and learning-based predictive control algorithms.