Symbolic State Estimation with Predicates for Contact-Rich Manipulation Tasks

TL;DR

This paper introduces a Bayesian symbolic state estimation method using predicate classifiers that effectively fuses noisy sensor data, requires minimal training data, and enhances robustness in contact-rich robotic manipulation tasks.

Contribution

It presents a novel Bayesian approach for symbolic state estimation in manipulation tasks, reducing data requirements and improving robustness over existing methods.

Findings

Accurately classifies symbolic states in real-world tasks

Generalizes well to unseen manipulation scenarios

Improves manipulation policy robustness on a real robot

Abstract

Manipulation tasks often require a robot to adjust its sensorimotor skills based on the state it finds itself in. Taking peg-in-hole as an example: once the peg is aligned with the hole, the robot should push the peg downwards. While high level execution frameworks such as state machines and behavior trees are commonly used to formalize such decision-making problems, these frameworks require a mechanism to detect the high-level symbolic state. Handcrafting heuristics to identify symbolic states can be brittle, and using data-driven methods can produce noisy predictions, particularly when working with limited datasets, as is common in real-world robotic scenarios. This paper proposes a Bayesian state estimation method to predict symbolic states with predicate classifiers. This method requires little training data and allows fusing noisy observations from multiple sensor modalities. We evaluate our framework on a set of real-world peg-in-hole and connector-socket insertion tasks, demonstrating its ability to classify symbolic states and to generalize to unseen tasks, outperforming baseline methods. We also demonstrate the ability of our method to improve the robustness of manipulation policies on a real robot.