PRAG: Procedural Action Generator

TL;DR

PRAG is a new procedural generator for creating complex, multi-step contact-rich manipulation tasks in robotics, validated through symbolic and physical checks, enabling scalable dataset creation for reinforcement learning.

Contribution

It introduces a novel method for automatically generating and validating complex robotic manipulation tasks, facilitating large-scale dataset creation for training.

Findings

Generated millions of unique solvable tasks

Validated tasks through symbolic and physical checks

Supported integration with existing robotic training frameworks

Abstract

We present a novel approach for the procedural construction of multi-step contact-rich manipulation tasks in robotics. Our generator takes as input user-defined sets of atomic actions, objects, and spatial predicates and outputs solvable tasks of a given length for the selected robotic environment. The generator produces solvable tasks by constraining all possible (nonsolvable) combinations by symbolic and physical validation. The symbolic validation checks each generated sequence for logical and operational consistency, and also the suitability of object-predicate relations. Physical validation checks whether tasks can be solved in the selected robotic environment. Only the tasks that passed both validators are retained. The output from the generator can be directly interfaced with any existing framework for training robotic manipulation tasks, or it can be stored as a dataset of curated robotic tasks with detailed information about each task. This is beneficial for RL training as there are dense reward functions and initial and goal states paired with each subgoal. It allows the user to measure the semantic similarity of all generated tasks. We tested our generator on sequences of up to 15 actions resulting in millions of unique solvable multi-step tasks.