From Tentacles to Trunks: The Future of Robotics with ConTac Technology
Researchers at JAIST have developed a breakthrough system, ConTac, which uses innovative sensing technology to enhance the safety and flexibility of continuum robots.
In nature, organisms like octopuses and elephants showcase remarkable dexterity with their tentacles and trunks, inspiring researchers to develop highly flexible robotic limbs often called continuum robots.
A continuum robot, characterized by many degrees of freedom (DOFs) and numerous joints, can dynamically adjust its shape to avoid obstacles. However, the complexity of their movements poses challenges in accurately characterizing their shape and motion. Traditional analytical techniques for solving kinematic and dynamic problems in continuum robots involve complex modelling, leading to high computational costs. Although flexible sensors can track shape and movement, they require numerous low-resolution sensors, resulting in cumbersome systems.
A promising alternative involves a single sensing module at the end of the continuum robot, but previous studies have focused on posture rather than contact detection. Addressing this gap, a research team from Japan, led by Associate Professor Van Anh Ho from the Japan Advanced Institute of Science and Technology (JAIST), developed a novel system called ConTac. This system can estimate the shape and contact of a robotic arm with soft skin.
“The ultimate goal of this system is to be implemented in a continuum robot, but in this study, we focused on perception using an articulated robotic arm and soft skin for verification,” explains Dr. Ho.
The research team included doctoral students Tuan Tai Nguyen and Quan Khanh Luu from JAIST, and Dr. Dinh Quang Nguyen from VNU-UET university in Hanoi. Their study was presented at the Robotics: Science and Systems (RSS 2024) conference held in Delft, Netherlands.
The ConTac system comprises a backbone mimicking the bending of a continuum robot, soft skin with markers, a camera to observe skin deformation, models for shape and contact sensing, and a contact-aware control regime. It can be applied to any ConTac unit or robot with the same mechanism without calibration. A ConTac unit is an assembled continuum-emulated robot arm with a backbone and soft skin. The researchers also developed an admittance-based controller using perceptual information to guide the robotic arm’s movements. Additionally, the ConTac unit is cost-effective, fabricated from conventional materials.
This innovative system uses two deep-learning models for shape reconstruction and contact detection of the soft skin. Trained entirely on simulation images, these models were directly adapted to real robots without fine-tuning, saving time and resources. The system’s transferability was tested on two different ConTac units, which performed similarly without additional adjustments.
Dr. Ho highlights the significance of this study: “The ConTac system is designed to be used in various robotic systems without complex adjustments. Flexible robotic arms equipped with our system are ideal for smart agriculture and healthcare services, where robots must navigate environments with many obstacles and interact safely with humans. Their softness and flexibility, combined with the ability to sense surroundings, make them perfect for interacting with plants and patients.”
The sensing and control principles in this framework could lead to new tactile sensors that can be attached to existing robotic systems, offering new paradigms for safe human-robot interaction without altering the robot’s original design.
Dr. Ho envisions a transformative future: “Imagine a society where every robot and machine possesses a sense of touch. This transformation would revolutionize industries and daily life.”
For more information, see the full conference submission: Continuum-Emulated Soft Skinned Arm with Vision-based Shape Sensing and Contact-aware Manipulation.
