Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Modular MANTA-RAY: A Modular Soft Surface Platform for Distributed Multi-Object Manipulation

Pratik Ingle, Jørn Lambertsen, Kasper Støy, Andres Faina

TL;DR

Manipulating diverse, fragile objects with rigid grippers is challenging due to high DOF and risk of damage; this work introduces Multi-Modular MANTA-RAY, a soft fabric-based surface with reduced actuator density to enable scalable manipulation over large areas. A distributed 2×2 modular architecture with shared actuators and a simple linear PID controller driven by a geometric transformation, plus an object-passing strategy, enables inter-module transfers and in-module control without heavy data-driven training. Validation spans MuJoCo simulations of larger grids ($3\times3$) and a physical 2×2 prototype, showing precise target reaching with mean errors below $0.02$ m and robust multi-object transfer within $0.03$ m. The results demonstrate scalable, parallel manipulation across modules and point to practical deployments in tasks such as food handling.

Abstract

Manipulation surfaces control objects by actively deforming their shape rather than directly grasping them. While dense actuator arrays can generate complex deformations, they also introduce high degrees of freedom (DOF), increasing system complexity and limiting scalability. The MANTA-RAY (Manipulation with Adaptive Non-rigid Textile Actuation with Reduced Actuation densitY) platform addresses these challenges by leveraging a soft, fabric-based surface with reduced actuator density to manipulate fragile and heterogeneous objects. Previous studies focused on single-module implementations supported by four actuators, whereas the feasibility and benefits of a scalable, multi-module configuration remain unexplored. In this work, we present a distributed, modular, and scalable variant of the MANTA-RAY platform that maintains manipulation performance with a reduced actuator density. The proposed multi-module MANTA-RAY platform and control strategy employs object passing between modules and a geometric transformation driven PID controller that directly maps tilt-angle control outputs to actuator commands, eliminating the need for extensive data-driven or black-box training. We evaluate system performance in simulation across surface configurations of varying modules (3x3 and 4x4) and validate its feasibility through experiments on a physical 2x2 hardware prototype. The system successfully manipulates objects with diverse geometries, masses, and textures including fragile items such as eggs and apples as well as enabling parallel manipulation. The results demonstrate that the multi-module MANTA-RAY improves scalability and enables coordinated manipulation of multiple objects across larger areas, highlighting its potential for practical, real-world applications.

Multi-Modular MANTA-RAY: A Modular Soft Surface Platform for Distributed Multi-Object Manipulation

TL;DR

Manipulating diverse, fragile objects with rigid grippers is challenging due to high DOF and risk of damage; this work introduces Multi-Modular MANTA-RAY, a soft fabric-based surface with reduced actuator density to enable scalable manipulation over large areas. A distributed 2×2 modular architecture with shared actuators and a simple linear PID controller driven by a geometric transformation, plus an object-passing strategy, enables inter-module transfers and in-module control without heavy data-driven training. Validation spans MuJoCo simulations of larger grids () and a physical 2×2 prototype, showing precise target reaching with mean errors below m and robust multi-object transfer within m. The results demonstrate scalable, parallel manipulation across modules and point to practical deployments in tasks such as food handling.

Abstract

Manipulation surfaces control objects by actively deforming their shape rather than directly grasping them. While dense actuator arrays can generate complex deformations, they also introduce high degrees of freedom (DOF), increasing system complexity and limiting scalability. The MANTA-RAY (Manipulation with Adaptive Non-rigid Textile Actuation with Reduced Actuation densitY) platform addresses these challenges by leveraging a soft, fabric-based surface with reduced actuator density to manipulate fragile and heterogeneous objects. Previous studies focused on single-module implementations supported by four actuators, whereas the feasibility and benefits of a scalable, multi-module configuration remain unexplored. In this work, we present a distributed, modular, and scalable variant of the MANTA-RAY platform that maintains manipulation performance with a reduced actuator density. The proposed multi-module MANTA-RAY platform and control strategy employs object passing between modules and a geometric transformation driven PID controller that directly maps tilt-angle control outputs to actuator commands, eliminating the need for extensive data-driven or black-box training. We evaluate system performance in simulation across surface configurations of varying modules (3x3 and 4x4) and validate its feasibility through experiments on a physical 2x2 hardware prototype. The system successfully manipulates objects with diverse geometries, masses, and textures including fragile items such as eggs and apples as well as enabling parallel manipulation. The results demonstrate that the multi-module MANTA-RAY improves scalability and enables coordinated manipulation of multiple objects across larger areas, highlighting its potential for practical, real-world applications.
Paper Structure (14 sections, 4 equations, 6 figures, 1 table, 1 algorithm)

This paper contains 14 sections, 4 equations, 6 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Multi-Modular MANTA-RAY
  3. Methods
  4. Hardware Setup:
  5. Simulation Setup:
  6. Controller
  7. Object Passing
  8. Position Control
  9. Results
  10. Object passing
  11. Object behavior
  12. Target reaching
  13. Multi-Object Manipulation
  14. Conclusion

Figures (6)

  • Figure 1: Multi-Modular MANTA-RAY: Manipulation with Adaptive Non-rigid Textile Actuation with Reduced Actuation densitY platform. (A) Manipulation of an egg and an apple. (B) Side view showing the platform dimensions of $1 \times 1 \times 0.7$ m (length, width, and height at rest). (C) Top view illustrating the arrangement of nine actuators (A0–A8) and four modules (M0–M3) without the flexible surface. (D) Each linear actuator has 0.4-meter vertical range and built using a stepper motor and pulley-belt mechanism, controlled by an Arduino Uno micro controller. (E) MuJoCo simulation of the extended $3\times3$-module configuration showing two objects (red and blue spheres) and their respective target locations.
  • Figure 2: Object Passing from M0 to M2 and back from M2 to M0
  • Figure 3: Mean Standard deviation comparison across objects during passing between modules
  • Figure 4: Square path of the object with three paths: Normal square (Blue), Small square (Purple) and Large square (Orange)
  • Figure 5: Target reaching for different objects on hardware platform. Object start at initial position (green circle) and move to target location (red star) within a threshold of 3 cm (red circle) along the line path.
  • ...and 1 more figures