8 March 2021 in IEEE Internet of Things Journal
Although vehicle location-based services are prevalent outdoors, we are back into darkness in many GPS blocked environments, such as tunnels, indoor parking garages, and multilevel flyovers. Existing smartphone-based solutions usually adopt inertial dead reckoning to infer the trajectory, but low-quality inertial sensors in phones are plagued by heavy noises, causing unbounded localization errors through double integrations for movements. In this article, we propose VeTorch, a smartphone inertial odometry that devises an inertial sequence learning framework to track vehicles in real time when GPS signal is not available. Specifically, we transform the inertial dynamics from the phone to the vehicle regardless of the arbitrary phone's placement in the car and explore a temporal convolutional network to learn the vehicle's moving dependencies directly from the inertial data. To tackle the heterogeneous smartphone properties and driving habits, we propose a federated learning-based active model training mechanism to produce customized models for individual smartphones, without incurring user privacy issues. We implement a highly efficient prototype and conduct extensive experiments on two large-scale real-world traffic data sets collected by a modern ride-hailing platform. Our results outperform the state-of-the-art vehicular inertial dead-reckoning solutions on both accuracy and efficiency.
16 February 2022 in IEEE Internet of Things Journal
Visual-based unsupervised learning [1] – [3] has emerged as a promising approach in estimating monocular depth and ego-motion, avoiding intensive efforts on collecting and labeling the ground truth. However, they are still restrained by the brightness constancy assumption among video sequences, especially susceptible with frequent illumination variations or nearby textureless surroundings in indoor environments. In this article, we selectively combine the complementary strength of visual and inertial measurements, i.e., videos extract static and distinct features while inertial readings depict scale-consistent and environment-agnostic movements, and propose a novel unsupervised learning framework to predict both monocular depth and ego-motion trajectory simultaneously. This challenging task is solved by learning both forward and backward inertial sequences to eliminate inevitable noises, and reweighting visual and inertial features via gated neural networks in various environments or with user-specific moving dynamics. In addition, we also employ structure cues to produce scene depths from a single image and explore structure consistency constraints to calibrate the depth estimates in indoor buildings. Experiments on the outdoor KITTI data set and our dedicated indoor prototype reveal that our approach consistently outperforms the state of the art on both depth and ego-motion estimates. To the best of our knowledge, this is the first work to fuse visual and inertial data without any supervision signals for monocular depth and ego-motion estimation, and our solution remain effective and robust even in textureless indoor scenarios.
4 March 2022 in IEEE Transactions on Instrumentation and Measurement
Nowadays, GPS and other global navigation satellite systems (GNSSs) have been widely developed, enabling accurate and convenient outdoor location-based services for vehicles. However, there is still a range of areas in an urban city that cannot be covered by satellites, e.g., large-scale tunnels, underground parking lots, and multilevel flyovers. Current vehicle inertial tracking methods always rely on dead-reckoning, but their performances are seriously affected by intrinsic fluctuations and external disturbances. Based on our experiments with thousands of smartphones, we summarize three threats for vehicle inertial tracking, i.e., arbitrary and unknown placements of smartphones during driving, volatile and inconstant noises on low-quality inertial sensors in commodity smartphones, and a diversity of smartphones and vehicles via crowdsensing. In this article, we explore a novel smartphone-based inertial learning framework to infer a vehicle’s location in real time. It contains a coordinate transformation algorithm to yield vehicle’s movements from smartphone’s inertial readings, an inertial sequence learning model to train and infer the trajectory instead of double integrations, and a customized model refinement mechanism to improve the tracking accuracy for individual drivers. Extensive experiments on the DiDi ride-hailing platform in two large cities have proved the effectiveness of our solution. In addition, our approach has been deployed on DiDi real-world mobile applications in 7.59 million devices and conducted 4.26 billion location inferences every day.
15 December 2021 in IEEE Transactions on Instrumentation and Measurement
Decorating speed bumps is a common and effective measure to compulsively reduce vehicular velocity in dangerous regions, especially at tunnels, slopes, and parking lots. Despite a decade of deployment, the bump information is still sporadic in map-based applications, for example, driving alert ahead of bumps. One major obstacle is the lack of an up-to-date bump database, thus service providers have to hire dedicated personnel to gather and periodically calibrate such data, which is effort-intensive and time-consuming to large-scale coverage. In this article, we propose a personal bump seeker (PBS), a novel mobile crowdsensing application to automatically identify and update speed bumps in urban cities. Specifically, we formulate bump detection as a regression model, thus improving the robustness of inertial patterns on temporal domain. We also explore a leader-follower mechanism that automatically extracts the bump signal for training and inference in individual smartphones, regardless of different smartphones, vehicles, and driving habits during crowdsensing. Finally, we implement a prototype and conduct extensive experiments on large-scale real-world traffic datasets collected by the DiDi platform, and the results demonstrate our effectiveness in producing a city-level bump database.