Efficient State Estimation with Constrained Rao-Blackwellized Particle Filter

TL;DR

This paper introduces a constrained Rao-Blackwellized Particle Filter that improves robotic object state estimation accuracy by enforcing physical constraints through quadratic programming, effectively filtering noisy sensor data.

Contribution

The paper presents a novel RBPF that incorporates physical constraints via quadratic programming, enhancing estimation accuracy and unobserved state inference in robotic manipulation.

Findings

More accurate object pose estimation.

Higher precision in unobserved state inference.

Effective noise filtering with physical constraints.

Abstract

Due to the limitations of the robotic sensors, during a robotic manipulation task, the acquisition of the object's state can be unreliable and noisy. Combining an accurate model of multi-body dynamic system with Bayesian filtering methods has been shown to be able to filter out noise from the object's observed states. However, efficiency of these filtering methods suffers from samples that violate the physical constraints, e.g., no penetration constraint. In this paper, we propose a Rao-Blackwellized Particle Filter (RBPF) that samples the contact states and updates the object's poses using Kalman filters. This RBPF also enforces the physical constraints on the samples by solving a quadratic programming problem. By comparing our method with methods that does not consider physical constraints, we show that our proposed RBPF is not only able to estimate the object's states, e.g., poses, more accurately but also able to infer unobserved states, e.g., velocities, with higher precision.