IMU Tracking of Kinematic Chains in the Absence of Gravitational and Magnetic Fields
March 07, 2024 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Greg K. Stretton, George Alex Koulieris
arXiv ID
2403.04357
Category
cs.HC: Human-Computer Interaction
Citations
1
Venue
arXiv.org
Last Checked
4 months ago
Abstract
Tracking kinematic chains has many uses from healthcare to virtual reality. Inertial measurement units, IMUs, are well-recognised for their body tracking capabilities, however, existing solutions rely on gravity and often magnetic fields for drift correction. As humanity's presence in space increases, systems that don't rely on gravity or magnetism are required. We aim to demonstrate the viability of IMU body tracking in a microgravity environment by showing that gravity and magnetism are not necessary for correcting gyroscope-based dead-reckoning drift. We aim to build and evaluate an end-to-end solution accomplishing this. A novel algorithm is developed that compensates for drift using local accelerations alone, without needing gravity or magnetism. Custom PCB sensor, IMU, nodes are created and combined into a body-sensor-network to implement the algorithm and the system is evaluated to determine its strengths and weaknesses. Dead-reckoning alone is accurate to within 1 degree for 30s. The drift correction solution can correct large drifts in yaw within 4 seconds of lateral accelerations to within 3.3 degrees RMSE. Correction accuracy when drift-free and under motion is 1.1 degrees RSME. We demonstrate that gyroscopic drift can be compensated for in a kinematic chain by making use of local acceleration information and often-discarded centripetal and tangential acceleration information, even in the absence of gravitational and magnetic fields. Therefore, IMU body tracking is a viable technology for use in microgravity environments.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted