Pratik Ingle https://pratik-ingle.github.io/posts/research/index.html Plain-language explanations of my research papers and research problems. quarto-1.0.37 Wed, 11 Mar 2026 23:00:00 GMT Scalable Surface-Based Manipulation Through Modularity https://pratik-ingle.github.io/posts/research/scalable-surface-based-manipulation/index.html

The problem

Robotic Manipulation Surfaces (RMS) move objects by deforming the surface they rest on. This makes them attractive for fragile, irregular, or food-like objects, where grasping can damage the item or require a specialized gripper. The difficulty is scale: dense actuator arrays can give fine control, but they become expensive and mechanically complex when the workspace grows.

The core idea

The paper asks whether a manipulation surface can be made modular. Instead of building one very dense surface, we connect fabric-based modules and coordinate object movement across module boundaries. Adjacent modules share edge actuators, reducing actuator count from 4n^2 to (n + 1)^2 for an n x n grid.

In a 2 x 2 prototype, this gives a 1 x 1 m workspace with only 9 actuators.

What makes it hard

Sharing actuators is efficient, but it mechanically couples neighboring modules. Moving one module can disturb objects on another module. The platform therefore needs both high-level path planning and low-level compensation.

Our framework combines:

  1. Manhattan-style conflict-free path planning.
  2. Directional object passing between modules.
  3. A geometric PID controller for positioning.
  4. Compensation strategies for passive-object disturbance.

Result

The system achieves coordinated inter-module transfer and sub-centimeter positioning for heterogeneous objects, including fragile items. Compensation reduced passive-object displacement by 59-78% across the measured configurations.

Why I care about this

For me, the interesting part is not only that a surface can move objects. It is that manipulation can be treated as a property of a distributed surface: hardware design, geometry, and control all contribute. That feels like a promising route toward scalable manipulation in logistics, food processing, and other settings where objects are too varied for one gripper.

Paper: arXiv:2601.21884

]]> research soft robotics manipulation https://pratik-ingle.github.io/posts/research/scalable-surface-based-manipulation/index.html Wed, 11 Mar 2026 23:00:00 GMT Linear Control on a Nonlinear Soft Surface https://pratik-ingle.github.io/posts/research/linear-control-nonlinear-soft-surface/index.html Soft robotic systems are nonlinear almost by definition: fabrics deform, objects slide and roll, friction changes, and contact geometry matters. It is tempting to assume the controller must also be complex.

Our CASE 2025 paper explores a more pragmatic question: how far can a simple linear controller go on a nonlinear soft manipulation surface?

Why simple control is worth testing

Simple controllers are easier to tune, debug, and deploy. When hardware is new, a controller that reveals the important system behavior can be more useful than an opaque controller that only works in a narrow setup.

The goal was not to claim that the surface is linear. It was to test whether a linear controller can still produce useful manipulation when the actuation and object response are nonlinear.

The manipulation loop

At a high level, the controller compares the current object position with the target, maps the error into actuator commands, and updates the surface shape. The soft surface then converts those changes into object motion.

The interesting part is that the controller can remain relatively simple while the physical surface performs much of the transformation.

Takeaway

For grasp-free manipulation, the controller and hardware should be designed together. The surface is not just a passive floor; it is part of the computation.

Paper: DOI

]]> research control soft robotics https://pratik-ingle.github.io/posts/research/linear-control-nonlinear-soft-surface/index.html Sat, 16 Aug 2025 22:00:00 GMT Soft Manipulation With Fewer Actuators https://pratik-ingle.github.io/posts/research/reduced-actuator-soft-manipulation-surface/index.html A common way to build a manipulation surface is to place many actuators under it. That can work, but it makes the platform expensive, mechanically dense, and difficult to scale.

In our RoboSoft 2025 paper, we explored a different design: a soft surface actuated by fewer vertical actuators, spaced far enough apart that the object can be much smaller than the distance between actuators. This creates a control problem because the surface is nonlinear and continuous, but it also creates a hardware opportunity: fewer actuators can cover a larger area.

What the surface does

The surface changes shape, and the object moves because gravity, contact geometry, and surface deformation combine into a controllable motion field. The robot does not grasp the object. It changes the world under the object.

Why heterogeneous objects matter

Real applications rarely contain one perfect object. Objects differ in weight, shape, size, fragility, and friction. A manipulation surface should not need a new gripper for every case.

That is why this line of work focuses on heterogeneous objects. The long-term question is whether a single soft surface can provide enough controllability while staying mechanically simple.

What I learned

Hardware simplicity moves complexity into modeling, sensing, and control. That tradeoff is not automatically good, but it is interesting: if the surface can be controlled robustly, sparse actuation makes the system much easier to scale.

Paper: DOI

]]> research soft robotics hardware https://pratik-ingle.github.io/posts/research/reduced-actuator-soft-manipulation-surface/index.html Mon, 21 Apr 2025 22:00:00 GMT