Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance, balancing accuracy and real-time inference remains a challenge. To address this, we propose a logits-based knowledge distillation framework for MOS, aiming to improve accuracy while maintaining real-time efficiency. Specifically, we adopt a Bird’s Eye View (BEV) projection-based model as the student and a non-projection model as the teacher. To handle the severe imbalance between moving and non-moving classes, we decouple them and apply tailored distillation strategies, allowing the teacher model to better learn key motion-related features. This approach significantly reduces false positives and false negatives. Additionally, we introduce dynamic upsampling, optimize the network architecture, and achieve a 7.69% reduction in parameter count, mitigating overfitting. Our method achieves a notable IoU of 78.8% on the hidden test set of the SemanticKITTI-MOS dataset and delivers competitive results on the Apollo dataset. The KDMOS implementation is available at https://github.com/SCNU-RISLAB/KDMOS.

Testing Autonomous Driving Systems (ADS) is critical for validating their safety in operational environments. High-fidelity simulators enable the testing of ADS through virtual driving scenarios, especially those that are hazardous to replicate in real-world settings. However, existing testing approaches suffer from inadequate coverage of real-world traffic situations due to over-simplified modeling of vehicle movements (e.g., insufficient diversity in driving styles), resulting in undetected critical ADS failures. In this article, we propose a testing framework to discover diverse failures of ADS in driving scenarios that embody real-world traffic complexity. The framework leverages advanced traffic simulation methods to encode vehicle movements and generates realistic yet safety-critical driving scenarios for ADS by mutating vehicle movements. To efficiently explore driving scenarios that pose different challenges for ADS and expose diverse ADS failures, this framework further leverages a dynamic prioritization mechanism that prioritizes vehicle movements likely to trigger unique ADS behaviors. Specifically, we propose a method to estimate the possibility based on encoded vehicle movements. We implement this framework and evaluate it with three representative ADS from the famous CARLA Leaderboard. Empirical evaluation demonstrates that the proposed approach discovers more unique failures of ADS than existing testing frameworks.

Autonomous driving emphasizes precise multi-sensor fusion positioning on limit resource embedded systems. LiDAR-centered sensor fusion system serves as a mainstream navigation system due to its insensitivity to illumination and viewpoint change. However, these types of systems suffer from handling large-scale sequential LiDAR data using limited resources on board, leading LiDAR-centralized sensor fusion unpractical. As a result, hand-crafted features such as plane and edge are leveraged in majority mainstream positioning methods to alleviate this unsatisfaction, triggering a new cornerstone in LiDAR Inertial sensor fusion. However, such super light weight feature extraction, although it achieves real-time constraint in LiDAR-centered sensor fusion, encounters severe vulnerability under high speed rotational or translational perturbation. In this paper, we propose a sparse tensor based LiDAR Inertial fusion method for autonomous driving embedded system. Leveraging the power of sparse tensor, the global geometrical feature is fetched so that the point cloud sparsity defect is alleviated. Inertial sensor is deployed to conquer the time-consuming step caused by the coarse level point-wise inlier matching. We construct our experiments on both representative dataset benchmarks and realistic scenes. The evaluation results show the robustness and accuracy of our proposed solution compared to classical methods.

Object segmentation is a per-pixel label prediction task that targets at providing context analysis for autonomous driving. Moving-object segmentation (MOS) serves as a subbranch of object segmentation, targeting to separating the surrounding objects into binary options: dynamic and static. MOS is vital for the safety-critical task in autonomous driving because dynamic objects are often a true potential threat to self-driving cars compared to static ones. Current methods typically address the MOS problem as a category feature to label the mapping task, which is not rational in reality. For example, a parking car should be considered as static instead of a moving-object category. There is a little systematic theory to differentiate object moving characteristics from nonmoving characteristics in MOS. Furthermore, restricted by limited resources in the embedded system, MOS is often in an offline manner due to huge computational requirements. An online and low computational cost MOS is an urgent demand for the practical safety-critical mission which takes immediate reaction as compulsory. In this article, we propose EmPointMovSeg, an efficient and practical 3-D LiDAR MOS solution for autonomous driving. Leveraging the power of the well-adapted autoregressive system identification (AR-SI) theory, EmPointMovSeg theoretically explains the moving-object feature in large-scale 3-D LiDAR semantic segmentation. An end-to-end sparse tensor-based CNN which balances segmentation accuracy and online process ability is proposed. We construct our experiment on both representative dataset benchmarks and practical embedded systems. The evaluation result shows the effectiveness and accuracy of our proposed solution, conquering the bottleneck in the online large-scale 3-D LiDAR semantic segmentation.

Combining multiple sensors enables a robot to maximize its perceptual awareness of environments and enhance its robustness to external disturbance, crucial to robotic navigation. This paper proposes the FusionPortable benchmark, a complete multi-sensor dataset with a diverse set of sequences for mobile robots. This paper presents three contributions. We first advance a portable and versatile multi-sensor suite that offers rich sensory measurements: 10Hz LiDAR point clouds, 20Hz stereo frame images, high-rate and asynchronous events from stereo event cameras, 200Hz inertial readings from an IMU, and 10Hz GPS signal. Sensors are already temporally synchronized in hardware. This device is lightweight, self-contained, and has plug-and-play support for mobile robots. Second, we construct a dataset by collecting 17 sequences that cover a variety of environments on the campus by exploiting multiple robot platforms for data collection. Some sequences are challenging to existing SLAM algorithms. Third, we provide ground truth for the decouple localization and mapping performance evaluation. We additionally evaluate state-of-the-art SLAM approaches and identify their limitations. The dataset, consisting of raw sensor measurements, ground truth, calibration data, and evaluated algorithms, will be released.

Control-CPS software fault localization (SFL, aka bug localization) is of critical importance as bugs may cause major failures, even injuries/deaths. To locate the bugs in control-CPSs, SFL tools often demand many labeled ("correct"/"incorrect") source code execution traces as inputs. To label the correctness of these traces, we must judge the corresponding control-CPS physical trajectories' correctness. However, unlike discrete outputs, the boundaries between correct and incorrect physical trajectories are often vague. The mechanism (aka oracle) to judge the physical trajectories' correctness thus becomes a major challenge. So far, the ad hoc practice of ``human oracles'' is still widely used, whose qualities heavily depend on the human experts' expertise and availability. This paper proposes an oracle based on the well adopted autoregressive system identification (AR-SI). With proven success for controlling black-box physical systems, AR-SI is adapted by us to identify the buggy control-CPS as a black-box. We use this identification result as an oracle to judge the control-CPS's behaviors, and propose a methodology to prepare traces for control-CPS debugging. Comprehensive evaluations on classic control-CPSs with injected real-life and artificial bugs show that our proposed approach significantly outperforms the human oracle approach in SFL accuracy (recall) and latency, and in oracle false positive/negative rates. Our approach also helps discover a new real-life bug in a consumer-grade control-CPS.

By virtue of gravity measurement from a handheld inertial measurement unit (IMU) sensor, current indoor attitude estimation algorithms can provide accurate roll/pitch dimension angles. Acquisition of precise heading is limited by the absence of accurate magnetic reference. Consequently, initial stage magnetometer calibration is deployed to alleviate this bottleneck in attitude fusion. However, available algorithms tackle magnetic distortion based on time-invariant surroundings, casting the post-calibration magnetic data into unchanged ellipsoid centered in the calibration place. Consequently, inaccurate fusion results are formulated in a more common case of random walk in time-varying magnetic indoor environment. This article proposes a new fusion algorithm from various kinds of IMU sensors, namely gyroscope, accelerometer, and magnetometer. Compared to state-of-the-art attitude fusion approaches, this article addresses the indoor time-varying magnetic perturbation problem in a geometric view. We propose an extend Kalman filter--based algorithm based on this detailed geometric model to eliminate the position-dependent effect of a compass sensor. Experimental data demonstrate that, under different indoor magnetic distortion environments, our proposed attitude fusion algorithm has the maximum angle error of 2.02°, outperforming 7.17° of a gradient-declining-based algorithm. Additionally, this attitude fusion result is constructed in a low-cost handheld arduino core--based IMU device, which can be widely applied to embedded systems.

We propose a cyber-physical system of unmanned quadcopters to locate air pollution sources in a timely manner. The system consists of a physical part and a cyber part. The physical part includes unmanned quadcopters equipped with multiple sensors. The cyber part carries out control laws. We simplify the control laws by decoupling the quadcopters’ horizontal-plane motion control from vertical motion control. To control the quadcopter’s horizontal-plane motions, we propose a controller that combines pollutant dynamics with quadcopter physics. To control the quadcopter’s vertical motions, we adopt an anti-windup proportional-integral (PI) controller. We further extend the horizontal-plane control laws from a single quadcopter to multiple quadcopters. The multi-quadcopter control laws are distributed and convergent. We implement a prototype quadcopter and carry out experiments to verify the vertical control laws. We also carry out simulations to evaluate the horizontal-plane control laws. With quadcopter parameters set commensurate with our prototype implementation’s, our simulations show that the control laws can drive quadcopters to locate pollution source(s) in a timely way.

With the emergence of many commercial-off-the-shelf (COTS) and/or open-source hardware and software, we can now build cheap Unmanned Aerial Vehicles (UAVs). This will enable a broad spectrum of potential UAV based mobile applications. In this work, we propose a simple open UAV platform: Ard-μ-copter. Ard-μ-copter is a quadcopter built upon the open source ArduPilot [1] infrastructure library and hardware. Comparing to the many existing commercial quadcopters platforms and open source quadcopter platforms, Ard-μ-copter platform is fully open source, simple (i.e. what the "μ" stands for), and with good documentations.

Hyperspectral image classification has been a very active area of research in recent years. It faces challenges related with the high dimensionality of the data and the limited availability of training samples. In order to address these issues, subspace-based approaches have been developed to reduce the dimensionality of the input space in order to better exploit the (limited) training samples available. An example of this strategy is a recently developed subspace-projection-based multinomial logistic regression technique able to characterize mixed pixels, which are also an important concern in the analysis of hyperspectral data. In this letter, we extend the subspace-projection-based concept to support vector machines (SVMs), a very popular technique for remote sensing image classification. For that purpose, we construct the SVM nonlinear functions using the subspaces associated to each class. The resulting approach, called SVMsub, is experimentally validated using a real hyperspectral data set collected using the National Aeronautics and Space Administration's Airborne Visible/Infrared Imaging Spectrometer. The obtained results indicate that the proposed algorithm exhibits good performance in the presence of very limited training samples.

Traditional urban cellular automata (CA) model can effectively simulate infilling and edge-expansion growth patterns. However, most of these models are incapable of simulating the outlying growth. This paper proposed a novel model called LEI-CA which incorporates landscape expansion index (LEI) with CA to simulate urban growth. Urban growth type is identified by calculating the LEI index of each cell. Case-based reasoning technique is used to discover different transition rules for the adjacent growth type and the outlying growth type, respectively. We applied the LEI-CA model to the simulation of urban growth in Dongguan in southern China. The comparison between logistic-based CA and LEI-CA indicates that the latter can yield a better performance. The LEI-CA model can improve urban simulation accuracy over logistic-based CA by 13.8%, 10.8% and 6.9% in 1993, 1999 and 2005, respectively. Moreover, the outlying growth type hardly exists in the simulation by logistic-based CA, while the proposed LEI-CA model performs well in simulating different urban growth patterns. Our experiments illustrate that the LEI-CA model not only overcomes the deficiencies of traditional CA but might also better understand urban evolution process.