Evaluating Tracking Rotations Using Maximal Entropy Distributions for Smartphone Applications

Brotchie, James; Li, Wenchao; Kealy, Allison; Moran, Bill

doi:10.1109/access.2021.3135012

Cited by 2 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 24 ], the authors present TLIO, again using ResNet, to regress 3D displacement estimates and the uncertainty, allowing them to tightly fuse the relative state measurement into a stochastic cloning extended Kalman filter (EKF) to solve for pose, velocity and sensor biases. Owing to its reliance on an EKF, it was shown to be susceptible to a system failure during highly dynamic or unusual motion, which is in line with previous work [ 25 ]. Similarly, in [ 26 ], the authors propose a hybridised approach using an LSTM and EKF in a modular design that consists of orientation and position subsystems, termed IDOL.…”

Section: Related Worksupporting

confidence: 86%

RIOT: Recursive Inertial Odometry Transformer for Localisation from Low-Cost IMU Measurements

Brotchie

Greentree

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Inertial localisation is an important technique as it enables ego-motion estimation in conditions where external observers are unavailable. However, low-cost inertial sensors are inherently corrupted by bias and noise, which lead to unbound errors, making straight integration for position intractable. Traditional mathematical approaches are reliant on prior system knowledge, geometric theories and are constrained by predefined dynamics. Recent advances in deep learning, which benefit from ever-increasing volumes of data and computational power, allow for data-driven solutions that offer more comprehensive understanding. Existing deep inertial odometry solutions rely on estimating the latent states, such as velocity, or are dependent on fixed-sensor positions and periodic motion patterns. In this work, we propose taking the traditional state estimation recursive methodology and applying it in the deep learning domain. Our approach, which incorporates the true position priors in the training process, is trained on inertial measurements and ground truth displacement data, allowing recursion and learning both motion characteristics and systemic error bias and drift. We present two end-to-end frameworks for pose invariant deep inertial odometry that utilises self-attention to capture both spatial features and long-range dependencies in inertial data. We evaluate our approaches against a custom 2-layer Gated Recurrent Unit, trained in the same manner on the same data, and tested each approach on a number of different users, devices and activities. Each network had a sequence length weighted relative trajectory error mean ≤0.4594 m, highlighting the effectiveness of our learning process used in the development of the models.

show abstract

Section: Related Worksupporting

confidence: 86%

RIOT: Recursive Inertial Odometry Transformer for Localisation from Low-Cost IMU Measurements

Brotchie

Greentree

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…A GRU was built, as previous work has shown that it outperforms Temporal Convolutions Networks and other RNN variants [32]. Additionally, we use a UKF, proven effective in attitude estimation in previous work [6].…”

Section: Baselinesmentioning

confidence: 99%

“…Most of the complexity in attitude estimation stems from its nonlinearity, and therefor its estimation solution must account for the nonlinear dynamics in the system. Early applications relied on the extended Kalman filter (EKF) to linearise the dynamic system about the current best-state estimate; however, this process can yield poor performance particularly in highly dynamic situations due to divergence and constant reinitialisation [6]. These difficulties led to the development of alternative filters, several of which retain the basic structure of the EKF; most notably the Unscented Kalman Filter (UKF) which, at the time of writing, is the industry standard.…”

Section: Introductionmentioning

confidence: 99%

“…A survey of nonlinear attitude estimators is found in [7]. Despite all the iterative improvement to Kalman-filter-based estimators over the years, they are still dependent upon system model assumptions, and a deviation from defined assumptions may lead to divergence or failure of the system [6,7]. The shared reliance on a set of parameters that need to be predetermined or situationally adjusted in order to achieve satisfactory results have such a profound influence over performance that entire bodies of work have been built around calculating these values optimally [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging Self-Attention Mechanism for Attitude Estimation in Smartphones

Brotchie

Shao

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Inertial attitude estimation is a crucial component of many modern systems and applications. Attitude estimation from commercial-grade inertial sensors has been the subject of an abundance of research in recent years due to the proliferation of Inertial Measurement Units (IMUs) in mobile devices, such as the smartphone. Traditional methodologies involve probabilistic, iterative-state estimation; however, these approaches do not generalise well over changing motion dynamics and environmental conditions, as they require context-specific parameter tuning. In this work, we explore novel methods for attitude estimation from low-cost inertial sensors using a self-attention-based neural network, the Attformer. This paper proposes to part ways from the traditional cycle of continuous integration algorithms, and formulate it as an optimisation problem. This approach separates itself by leveraging attention operations to learn the complex patterns and dynamics associated with inertial data, allowing for the linear complexity in the dimension of the feature vector to account for these patterns. Additionally, we look at combining traditional state-of-the-art approaches with our self-attention method. These models were evaluated on entirely unseen sequences, over a range of different activities, users and devices, and compared with a recent alternate deep learning approach, the unscented Kalman filter and the iOS CoreMotion API. The inbuilt iOS had a mean angular distance from the true attitude of 117.31∘, the GRU 21.90∘, the UKF 16.38∘, the Attformer 16.28∘ and, finally, the UKF–Attformer had mean angular distance of 10.86∘. We show that this plug-and-play solution outperforms previous approaches and generalises well across different users, devices and activities.

show abstract

Evaluating Tracking Rotations Using Maximal Entropy Distributions for Smartphone Applications

Cited by 2 publications

References 27 publications

RIOT: Recursive Inertial Odometry Transformer for Localisation from Low-Cost IMU Measurements

RIOT: Recursive Inertial Odometry Transformer for Localisation from Low-Cost IMU Measurements

Leveraging Self-Attention Mechanism for Attitude Estimation in Smartphones

Contact Info

Product

Resources

About