Probabilistic Object Tracking using a Range Camera

Abstract

We address the problem of tracking the 6-DoF pose of an object while it is being manipulated by a human or a robot. We use a dynamic Bayesian network to perform inference and compute a posterior distribution over the current object pose. Depending on whether a robot or a human manipulates the object, we employ a process model with or without knowledge of control inputs. Observations are obtained from a range camera. As opposed to previous object tracking methods, we explicitly model self-occlusions and occlusions from the environment, e.g, the human or robotic hand. This leads to a strongly non-linear observation model and additional dependencies in the Bayesian network. We employ a Rao-Blackwellised particle filter to compute an estimate of the object pose at every time step. In a set of experiments, we demonstrate the ability of our method to accurately and robustly track the object pose in real-time while it is being manipulated by a human or a robot.

Cited by in corpus (13)

• Object-Centric Task and Motion Planning in Dynamic Environments
• Depth-Based Object Tracking Using a Robust Gaussian Filter
• Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks
• Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
• 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
• se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
• Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
• Probabilistic Articulated Real-Time Tracking for Robot Manipulation
• Diverse Plausible Shape Completions from Ambiguous Depth Images
• Real-time Perception meets Reactive Motion Generation
• The Coordinate Particle Filter - A novel Particle Filter for High Dimensional Systems
• Grasp success prediction with quality metrics
• Depth Camera Based Particle Filter for Robotic Osteotomy Navigation