Introducing Geometric Constraint Expressions Into Robot Constrained Motion Specification and Control

Abstract

Abstract- T HE problem of robotic task definition and execution was pioneered by Mason, [1], who defined setpoint constraints where the position, velocity, and/or forces are expressed in one particular task frame for a 6-DOF robot. Later extensions generalized this approach to constraints in i) multiple frames, ii) redundant robots, iii) other sensor spaces such as cameras, and iv) trajectory tracking. Our work extends tasks definition to i) expressions of constraints, with a focus on expressions between geometric entities (distances and angles), in place of explicit set-point constraints, ii) a systematic composition of constraints, iii) runtime monitoring of all constraints (that allows for runtime sequencing of constraint sets via, for example, a Finite State Machine), and iv) formal task descriptions, that can be used by symbolic reasoners to plan and analyse tasks. This means that tasks are seen as ordered groups of constraints to be achieved by the robot's motion controller, possibly with different set of geometric expressions to measure outputs which are not controlled, but are relevant to assess the task evolution. Those monitored expressions may result in events that trigger switching to another ordered group of constraints to execute and monitor.For these task specifications, formal language definitions are introduced in the JSON-schema modeling language.

ProbRobScene: A Probabilistic Specification Language for 3D Robotic Manipulation Environments

“…A user can declaratively specify the task a robot must accomplish using a variety of different methods such as geometric constraints [22], temporal logic [23], or expression graphs [24]. Such approaches complement our work here, as a user can then specify both task and environment formally, and automatically verify their robotic system end to end (as in e.g., [25], [26]).…”

Imitation of Manipulation Skills Using Multiple Geometries

“…The consideration of geometry in manipulation skills has been investigated early on in robotics, including the pioneer work of Mason formalizing force control based on task geometry [12]. In most applications, three priority levels of safety, primary and auxiliary constraints constructed from task geometric primitives suffice to describe manipulation features [13].…”

Inferring the Geometric Nullspace of Robot Skills from Human Demonstrations

“…The modelling approach chosen to represent the skills greatly affects the variety of possible skills and their adaptability to different hardware and environments. Constraint-based skill models offer a powerful and flexible choice, allowing us to model geometric constraints on the configuration and operational spaces [4,5,6,7], allowable velocities [8], and also forces and torques [9,10,11,12,13]. Also, constraint-based approaches have proven to be amenable to semantic modelling using ontologies [14] and Authors Affiliation: 1 A*STAR Institute for Infocomm Research (I2R), Singapore, 2 A*STAR Human-centric AI (CHEEM) Programme, Institute of High Performance Computing, Singapore, 3 A*STAR Advanced Remanufacturing and Technology Centre (ARTC), Singapore.…”