From Composable Models to Correct-By-Construction Software for Contact-Rich Robotic Mobile-Manipulation Tasks
Sven Schneider, Vamsi Krishna Kalagaturu, Herman Bruyninckx, Nico Hochgeschwender
AI summary
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.