Peripheral control enabled by distributed sensing in an octopus-inspired soft robotic arm for autonomous underwater grasping

2026-05-12 · Source: Nature Machine Intelligence · Field: Technology & Digital — Robotics & Autonomous Systems, Artificial Intelligence & Machine Learning · Depth: Expert, extended

Summary

A new octopus-inspired soft robotic arm, 410 mm long and 40 mm in diameter at the base, has been developed with distributed optoelectronic mechanosensors embedded in its ten suction cups. Each suction cup integrates LEDs and phototransistors to detect contact force and direction via light reflection, achieving high sensitivity (~400 mV N−1 in the 0–2-N range) and directional accuracy (error, <18°). The sensors operate reliably in both dry and wet environments with minimal drift and hysteresis. The arm features a hierarchical control architecture, enabling local reflexes at the suction cup level and global coordination for autonomous grasping. This system reliably detects contact, estimates force and direction, and infers object position, demonstrating adaptive grasping in unstructured underwater environments. The design prioritizes compactness, low power consumption, and seamless integration, advancing sensor-integrated soft robotics.

Key takeaway

For robotics engineers developing autonomous manipulation systems, this octopus-inspired soft arm offers a validated approach to distributed sensing and control. You should consider integrating compact optoelectronic sensors and a hierarchical control architecture to achieve adaptive grasping in unstructured or underwater environments, reducing reliance on centralized processing and external perception systems. This design enables precise contact detection and force estimation, crucial for delicate or complex object interaction.

Key insights

Octopus-inspired soft robots with distributed optoelectronic sensing enable adaptive, autonomous grasping in complex environments.

Principles

• Distributed sensing enhances robotic autonomy.
• Bio-inspired hierarchical control simplifies complex movements.
• Optical sensors are suitable for soft body integration.

Method

The system uses optoelectronic mechanosensors in suction cups for contact detection, force/direction estimation, and object posture inference. A hierarchical control architecture then coordinates local suction reflexes with global tendon actuation for adaptive grasping.

In practice

• Integrate optoelectronic sensors for robust wet/dry tactile sensing.
• Implement hierarchical control for decentralized decision-making.
• Utilize coiled wires for flexible electronic connections in soft robots.

Topics

• Soft Robotics
• Octopus-inspired Design
• Distributed Sensing
• Optoelectronic Mechanosensors
• Hierarchical Control

Best for: AI Scientist, Robotics Engineer, Research Scientist

Related on AIssential

• Periodic Steady-State Control of a Handkerchief-Spinning Task Using a Parallel Anti-Parallelogram Tendon-driven Wrist — A novel tendon-driven wrist and hierarchical control enable precise, periodic manipulation of flexible objects like spinning handkerchiefs.
• Human-machine teaming dives underwater — Combining human and robot strengths is crucial for effective underwater human-robot teaming in challenging environments.
• A neural blueprint for human-like intelligence in soft robots — A neural-inspired AI control system enables soft robots to learn once and adapt instantly to diverse tasks and disturbances.
• Dense Force Estimation with an Event-based Optical Tactile Sensor — Event-based tactile sensors can reconstruct dense 3D force fields by mapping displacement data to forces via iFEM and neural networks.
• Leiden scientists 3D-print microrobots that “swim” without a brain — Microrobots can achieve complex navigation through physical design and environmental feedback, not just electronics.
• NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation — Robots can infer binary contact states for dexterous manipulation by fusing RGB-D vision and proprioception, offering a scalable alternative to hardware tactile sensors.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Nature Machine Intelligence.