Abstract:Distracted driver activity recognition plays a critical role in risk aversion-particularly beneficial in intelligent transportation systems. However, most existing methods make use of only the video from a single view and the difficulty-inconsistent issue is neglected. Different from them, in this work, we propose a novel MultI-camera Feature Integration (MIFI) approach for 3D distracted driver activity recognition by jointly modeling the data from different camera views and explicitly re-weighting examples based on their degree of difficulty. Our contributions are two-fold: (1) We propose a simple but effective multi-camera feature integration framework and provide three types of feature fusion techniques. (2) To address the difficulty-inconsistent problem in distracted driver activity recognition, a periodic learning method, named example re-weighting that can jointly learn the easy and hard samples, is presented. The experimental results on the 3MDAD dataset demonstrate that the proposed MIFI can consistently boost performance compared to single-view models.
Abstract:A reliable pose estimator robust to environmental disturbances is desirable for mobile robots. To this end, inertial measurement units (IMUs) play an important role because they can perceive the full motion state of the vehicle independently. However, it suffers from accumulative error due to inherent noise and bias instability, especially for low-cost sensors. In our previous studies on Wheel-INS \cite{niu2021, wu2021}, we proposed to limit the error drift of the pure inertial navigation system (INS) by mounting an IMU to the wheel of the robot to take advantage of rotation modulation. However, it still drifted over a long period of time due to the lack of external correction signals. In this letter, we propose to exploit the environmental perception ability of Wheel-INS to achieve simultaneous localization and mapping (SLAM) with only one IMU. To be specific, we use the road bank angles (mirrored by the robot roll angles estimated by Wheel-INS) as terrain features to enable the loop closure with a Rao-Blackwellized particle filter. The road bank angle is sampled and stored according to the robot position in the grid maps maintained by the particles. The weights of the particles are updated according to the difference between the currently estimated roll sequence and the terrain map. Field experiments suggest the feasibility of the idea to perform SLAM in Wheel-INS using the robot roll angle estimates. In addition, the positioning accuracy is improved significantly (more than 30\%) over Wheel-INS. Source code of our implementation is publicly available (https://github.com/i2Nav-WHU/Wheel-SLAM).
Abstract:A reliable self-contained navigation system is essential for autonomous vehicles. In this study, we propose a multiple microelectromechanical system (MEMS) inertial measurement unit (IMU)-based dead reckoning (DR) solution for wheeled vehicles. The IMUs are located at different places on the wheeled vehicle to acquire various dynamic information. In the proposed system, at least one IMU has to be mounted at the wheel to measure the wheel velocity, thus, replacing the traditional odometer. The other IMUs can be mounted on either the remaining wheels or the vehicle body. The system is implemented through a decentralized extended Kalman filter structure in which each subsystem (corresponding to each IMU) retains and updates its own states separately. The relative position constraint between the IMUs is exploited by fusing the IMU positions to calculate the coordinates of the reference point, which is treated as an external observation of the subsystems. Specially, we present the DR systems based on dual wheel-mounted IMUs (Wheel-IMUs), one Wheel-IMU plus one vehicle body-mounted IMU (Body-IMU), and dual Wheel-IMUs plus one Body-IMU as examples for analysis and experiments. Field tests illustrate that the proposed multiple IMU-based DR system statistically outperforms the single Wheel-IMU based DR system in positioning and heading accuracy. Moreover, of the three multi-IMU configurations, the one Body IMU plus one Wheel-IMU design obtains the minimum drift rate.
Abstract:A self-contained autonomous navigation system is desired to complement the Global Navigation Satellite System (GNSS) for land vehicles, for which odometer aided inertial navigation system (ODO/INS) is a classical solution. In this study, we use a wheel-mounted MEMS IMU (Wheel-IMU) to substitute the conventional odometer, and further, investigate three types of measurement models, including the velocity measurement, displacement increment measurement, and contact point zero-velocity measurement, in the Wheel-IMU based dead reckoning (DR) system. The three measurements, along with the non-holonomic constraints (NHCs) are fused with INS by an extended Kalman filter (EKF). Theoretical discussion and field tests illustrate their feasibility and equivalence in overall positioning performance, which have the maximum horizontal position drifts less than 2% of the total travelled distance. However, the displacement increment measurement model is less sensitive to the installation lever arm between the Wheel-IMU and wheel center.
Abstract:Microelectromechanical systems (MEMS) based inertial navigation systems (INS) are widely used for robot navigation as they are self-contained and low-cost for motion perception. Various methods have been utilized to restrict the error growth caused by the inherent inertial sensor noises. Inspired by the rotation-modulation INS that using intentional rotation to mitigate the drift errors, we propose an integrated navigation solution for mobile robots based on a single wheel mounted MEMS IMU. The IMU is leveraged to produce odometry measurements with wheel radius and estimate the wheel motion. Zero-type constraints and the vehicle motion constraints are also introduced to limit the navigation errors. Field experiments prove that the rotation scheme can effectively reduce the heading error. The horizontal position accuracy of the proposed system is two times better than the conventional odometry aided INS for large-scale polyline trajectory tests. The cancellation effect of the track on navigation errors drift is also illustrated.