Harris, L. R., Jörges, B., Bury, N., McManus, M., Basanai, A., Allison, R. S, Jenkin, M. Can visual acceleration evoke a sensation of tilt? Exp. Brain Res. 243(3), 68, 2025.
Under the microgravity of the International Space Station, many of the normal processes that determine the perceptual upright on Earth are disrupted. For example, somatosensory cues are absent and an applied physical linear acceleration can provide an artificial “gravity” reference. Here, we hypothesized that visual linear acceleration could also be interpreted as an orientation cue in microgravity. Using virtual reality, we subjected twelve astronauts experiencing long-duration exposure to microgravity to visually simulated accelerating linear self-motion along a virtual corridor at 0.8 m•s− 2 (0.083 G) for 16s. They then adjusted a virtual ground plane to indicate whether they had changed their perceived orientation. Control experiments used visually simulated linear self-motion at a constant velocity and control experiments on Earth mirrored the experiments conducted in microgravity in both upright and supine postures. Contrary to our hypothesis, no significant perceptual tilts were induced on Earth or in microgravity. However, we did replicate earlier results that both microgravity exposure (in comparison to on Earth) and a supine posture (in comparison to a sitting upright posture) were associated with higher variability in judgements of upright. Our experiments failed to demonstrate that exposure to visual acceleration can evoke a sense of tilt in a stationary observer in the dark, either in microgravity or on Earth.
Wu, D., Jenkin, M., Xu, Y. T., Liu, X., Chen, X., Dudek, G. L. Method of load forecasting via attentive knowledge transfer, and an apparatus for the same. US Patent 12,335,107, 2025.
A method of forecasting a future load may include: obtaining source data sets and a target data set that have been collected from a plurality of source base stations and a target base station, respectively; among a plurality of source machine learning models, selecting at least one machine learn source model that has a traffic load prediction performance higher than that of a target machine learning model through a negative transfer analysis; obtaining model weights to be applied to the target machine learning model and the selected at least one source machine learning model via an attention neural network that is jointly trained with the target machine learning model and the selected source machine learning models; obtaining a load forecasting model for the target base station by combining the target machine learning model and the selected at least one source machine learning model according to the model weights; and predicting a future communication traffic load of the target base station based on the load forecasting model.
Harris, L. R., Allison, R., Jenkin, M., Herpers, R. Bury, N. and Schellen, E. Sex and the Somatogravic Illusion. Proc. Vestibular-Oriented Research Meeting, May, 2025. Abstract published in J. Vest. Res. June 18, 2025
Linear accelerations in the absence of visual cues to upright can be interpreted as tilt: the well-known somatogravic illusion. Here we provided linear acceleration using a human centrifuge and compared the induced tilt of the gravito-inertial acceleration to the precision and accuracy of responses to comparable physical tilt in the dark either while lying flat on a tilt table or while seated on a tiltable chair, to explore the connection between applied acceleration, posture and the perception of upright. Preliminary results (Herpers et al., 2019) had suggested possible sex differences in which women were less vulnerable to the somatogravic illusion than men. Here we sought to confirm any such differences within larger populations (centrifuge/tilt table: 44 participants, 22 females; tilt chair: 42 participants, 21 females) using head-in and head-out centrifugal forces of 0, 0.33 g, 0.66 g and 1 g compared to physical tilts between 0° (horizontal) and ±45° while lying on the tilt table or while seated in the tilt chair. No sex-related differences were found either in the response to centrifugation or to physical tilt while lying. Participants consistently over-estimated their tilt when seated, with women making consistently smaller errors. These results suggest posture-dependent sex differences during tilt which do not affect the magnitude of people’s somatogravic illusion.
Codd-Downey, R. and Jenkin, M. Diver to robot communication underwater. Proc. IEEE ICRA. Atlanta, GA. March, 2025.
Gesture-based communication is a standard underwater communication strategy that is taught to divers as part of their regular diver training and it would seem a natural mechanism to leverage for diver to robot communication underwater. Enabling an unmanned underwater vehicle (UUV) to understand such sequences would involve having the robot learn the large set of gestures that divers use and the way they are combined. As perfect transcription of gestures is unlikely, the communication process also requires an error-correcting framework to ensure that communication is clear and correct. Here we describe an interactive process that provides this infrastructure. A weakly supervised transfer learning approach is used to recognize standard SCUBA gestures in individual video frames and within a Sim2Real process to train a LSTM to recognize gesture sequences. This process is placed within a per-gesture and per-sequence interaction process to assist and confirm the recognition of individual gestures and to confirm entire gesture sequences. Individual aspects of this process and complete end-to-end operation are demonstrated using an unmanned underwater vehicle.
Brown, J., Farkhatdinov, I. and Jenkin, M. ROV Teleoperation in the Presence of Cross-Currents Using Soft Haptics. Journal of Field Robotics. Feb 23, 2025.
The remote operation of underwater vehicles at depth is complicated by the presence of invisible and unpredictable environmental disturbances such as cross-currents. Communicating the presence of these disturbances to an operator on the surface is made more difficult by the nature of the disturbances and the lack of visible features to highlight in the visual display presented to the operator. Here we explore the use of a novel interactive soft haptic touchpad that utilizes vibration and particle jamming to provide information about the presence and direction of cross-currents to the operator of an ROV (remotely operated vehicle). An in-water experiment using a thruster-based ROV and artificially generated cross-current was performed with nonexpert ROV operators to evaluate the effectiveness of multimodal haptic feedback to communicate complex environmental information during high-risk operations. Advanced haptic displays can signal both the presence of external factors as well as their direction, information that can enhance operational performance as well as reduce operator cognitive load. Using haptic feedback resulted in a statistically significant reduction in cognitive load of 24.3% and an increase in positioning accuracy of 28.3% for novice operators. Deviation from an ideal path was also reduced by 29.5% for experienced operators when using haptic feedback compared to without. While this experiment took place in controlled conditions with a fixed direction cross-current and haptic interface, this approach could be extended to communicate real-time environmental information in real-world unstructured environments.
Harris, L. R. and Jenkin, M. Visual-vestibular integration in Challenging Environments. Cambridge Elements: Perception. Cambridge University Press, 2025.
This Element reviews the current state of what is known about the visual and vestibular contributions to our perception of self-motion and orientation with an emphasis on the central role that gravity plays in these perceptions. The Element then reviews the effects of impoverished challenging environments that do not provide full information that would normally contribute to these perceptions (such as driving a car or piloting an aircraft) and inconsistent challenging environments where expected information is absent, such as the microgravity experienced on the International Space Station.
Jilani, A., Hogan, F., Morissette, C., Dudek, G., Jenkin, M. and Siddiqi, K. Visual-tactile inference of 2.5D object shape from marker texture. IEEE Robotics and Automation Letters 10:1042-1049, 2025.
Visual-tactile sensing affords abundant capabilities for contact-rich object manipulation tasks including grasping and placing. Here we introduce a shape-from-texture inspired contact shape estimation approach for visual-tactile sensors equipped with visually distinct membrane markers. Under a perspective projection camera model, measurements related to the change in marker separation upon contact are used to recover surface shape. Our approach allows for shape sensing in real time, without requiring network training or complex assumptions related to lighting, sensor geometry or marker placement. Experiments show that the surface contact shape recovered is qualitatively and quantitatively consistent with those obtained through the use of photometric stereo, the current state of the art for shape recovery in visual-tactile sensors. Importantly, our approach is applicable to a large family of sensors not equipped with photometric stereo hardware, and also to those with semi-transparent membranes. The recovery of surface shape affords new capabilities to these sensors for robotic applications, such as the estimation of contact and slippage in object manipulation tasks (Hogan etal., 2022) and the use of force matching for kinesthetic teaching using multimodal visual-tactile sensing (Ablett etal., 2024)
Lin, W., Wu, D. and Jenkin, M. "Electric Load Forecasting for Individual Households via Spatial-Temporal Knowledge Distillation," in IEEE Transactions on Power Systems, vol. 40, no. 1, pp. 572-584, Jan. 2025
Short-term load forecasting (STLF) for residential households has become of critical importance for the secure operation of power grids as well as home energy management systems. While machine learning is effective for residential STLF, data and resource limitations hinder individual household predictions operated on local devices. In contrast, utility companies have access to broader sets of data as well as to better computational resources, and thus have the potential to deploy complex forecasting models such as Graph neural network-based models to explore the spatial-temporal relationships between households for achieving impressive STLF performance. In this work, we propose an efficient and privacy-conservative knowledge distillation-based STLF framework. This framework can improve the STLF forecasting accuracy of lightweight individual household forecasting models via leveraging the benefits of knowledge distillation and graph neural networks (GNN). Specifically, we distill the knowledge learned from a GNN model pre-trained on utility data sets into individual models without the need to access data sets of other households. Extensive experiments on real-world residential electric load datasets demonstrate the effectiveness of the proposed method.
