Research Analyzer
← Back ICRA 2026

From Composable Models to Correct-By-Construction Software for Contact-Rich Robotic Mobile-Manipulation Tasks

Sven Schneider, Vamsi Krishna Kalagaturu, Herman Bruyninckx, Nico Hochgeschwender

PDF

AI summary

Key figure (auto-extracted from paper)
A graph-structured task specification format enables automatic verification and correct-by-construction code generation for contact-rich robotic manipulation.
Composable models Correct-by-construction Task specification JSON-LD Mobile manipulation Constraint-based control

Problem

Existing domain-specific languages for specifying contact-rich tasks suffer from anti-patterns like poor composability, implicit assumptions, and tight coupling, which prevent unambiguous computer interpretation and safe code generation.

Approach

The authors design a graph-based interchange format using JSON-LD and SHACL to model geometric primitives, constraints, and controllers compositionally, enabling structural verification and automated code generation.

Key results

  • Analysis of anti-patterns in existing task specification DSLs
  • Design of composable metamodels using JSON-LD and SHACL
  • Implementation of tooling for model verification and code generation
  • Demonstration of workspace alignment on a mobile manipulator

Why it matters

Enables safer, reusable, and framework-independent task specifications for high-assurance robotic systems, reducing bugs in contact-rich manipulation software.

Abstract

Software frameworks like the Stack of Tasks (SoT), the Stanford Whole-Body Control (WBC) library, or the instanta- neous Task Specification using Constraints (iTaSC) have enabled robots to perform advanced, contact-oriented manipulation tasks. jgeom constr and eTaSL are among the few formal, computer- interpretable languages that allow users to specify such tasks independent of these frameworks. We analyse these languages for their limitations with respect to composability, the design for extensibility without having to change existing models, and compositionality, meaning that the semantics of compositions unambiguously follows from the semantics of the components and of the composition relations. To overcome these limitations we design a graph-structured and well-defined interchange format for such tasks. The associated tooling enables us to generate correct-by-construction code that adheres to predefined rules and constraints. We showcase our models and toolchain by incrementally constructing a workspace-alignment application for a highly-redundant mobile platform that is equipped with two 7-DoF, torque-controlled manipulators.

Index terms

Software Tools for Robot Programming Methods and Tools for Robot System Design Mobile Manipulation

Related papers