Road collapses seriously threaten human safety in cities. The effective and rapid identification of hidden urban road hazards using 3D ground-penetrating radar (3D-GPR) data is crucial for preventing and controlling road collapse accidents. We propose a novel intelligent identification method for urban road hazards using a backpropagation (BP) artificial neural network based on multiscale gray-level co-occurrence matrix (GLCM) attributes derived from 3D-GPR data. The characteristic differences in multiscale GLCM attributes between hidden hazards and other detected targets are leveraged to construct a road hazard identification model using a BP neural network. This model is applied to identify hazards from 3D-GPR data, enabling rapid localization of hidden urban road hazards. Initially, GPR data are processed using zero-time correction, background suppression, and filtering. Next, labeled data are created using the radar responses of known hazards, wells, pipelines, and strata. Subsequently, after applying gradient enhancement processing to the GPR data, the GLCM attributes are calculated at different scales to distinguish hazards in three-dimensional space from other target bodies. Finally, a neural network model for hidden hazard identification is constructed using a backpropagation (BP) artificial neural network and applied to identify hidden hazards beneath urban roads from GPR measurement data. The results show that the prediction accuracy exceeds 85% using the proposed approach. The combination of multi-scale GLCM attributes and BP neural network is valuable and effective for the detection and identification of hidden hazards beneath urban roads.

The field of aerial manipulation has seen rapid advances, transitioning from push-and-slide tasks to interaction with articulated objects. The motion trajectory of these complex actions is usually hand-crafted or a result of online optimization methods like Model Predictive Control (MPC) or Model Predictive Path Integral (MPPI) control. However, these methods rely on heuristics or model simplifications to efficiently run on onboard hardware, limiting their robustness, and making them sensitive to disturbances and differences between the real environment and its model. In this work, we propose a Reinforcement Learning (RL) approach to learn reactive motion behaviors for a manipulation task while producing policies that are robust to disturbances and modeling errors. Specifically, we train a policy to perform a door-opening task with an Omnidirectional Micro Aerial Vehicle (OMAV). The policy is trained in a physics simulator and shown in the real world, where it is able to generalize also to door closing tasks never seen in training. We also compare our method against a state-of-the-art MPPI solution in simulation, showing a considerable increase in robustness and speed.

Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin, Weixuan Zhang, Tisha Anders, Bill Byrne. Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2023.

Model-based controllers on real robots require accurate knowledge of the system dynamics to perform optimally. For complex dynamics, first-principles modeling is not sufficiently precise, and data-driven approaches can be leveraged to learn a statistical model from real experiments. However, the efficient and effective data collection for such a data-driven system on real robots is still an open challenge. This paper introduces an optimization problem formulation to find an informative trajectory that allows for efficient data collection and model learning. We present a sampling-based method that computes an approximation of the trajectory that minimizes the prediction uncertainty of the dynamics model. This trajectory is then executed, collecting the data to update the learned model. We experimentally demonstrate the capabilities of our proposed framework when applied to a complex omnidirectional flying vehicle with tiltable rotors. Using our informative trajectories results in models which outperform models obtained from non-informative trajectory by 13.3% with the same amount of training data. Furthermore, we show that the model learned from informative trajectories generalizes better than the one learned from non-informative trajectories, achieving better tracking performance on different tasks.

This work presents a method to control omnidirectional micro aerial vehicles (OMAVs) for the tracking of 6-DoF trajectories in free space. A rigid body model based approach is applied in a receding horizon fashion to generate optimal wrench commands that can be constrained to meet limits given by the mechanical design and actuators of the platform. Allocation of optimal actuator commands is performed in a separate step. A disturbance observer estimates forces and torques that may arise from unmodeled dynamics or external disturbances and fuses them into the optimization to achieve offset-free tracking. Experiments on a fully overactuated MAV show the tracking performance and compare it against a classical PD-based controller.

Anomaly detection in hyperspectral images aims to separate the abnormal pixels from the background, and becomes an important application of hyperspectral data processing. Anomaly detection based on Low-Rank and Sparse Representation (LRASR) can detect abnormal pixels accurately. However, with the growth of the hyperspectral data volumes, this algorithm consumes a huge amount of time and computational resources, and needs to be improved accordingly. Spark is a distributed big data processing platform, and is applicable for complex iterative calculations, because of its powerful in-memory computation and efficient task scheduling. Based on Spark, this paper proposes a distributed and parallel LRASR (called DP-LRASR), which first segments hyperspectral images using narrow dependency of resilient distributed datasets, and afterwards, a parallel clustering algorithm is employed to improve the efficiency, remarkably. Experimental results demonstrate that DP-LRASR achieves a good speedup with high scalability, in the premise of remarkable detection accuracy.

As the volume and value of hyperspectral remote sensing images increasing, a common hyperspectral imagery repository is urgently required. This paper presents a novel distributed content retrieval method for hyperspectral imagery repository based on cloud computing platform. The proposed method uses a software-as-a-service (SaaS) mode, which provides users with services such as hyperspectral image management, storage and retrieval through a web interface. In order to accelerate the acquisition of the spectral feature information needed in the retrieval process, we optimize the procedure of endmember extraction and the abundance estimation in a distributed way on Spark platform. The generated spectral features meta-data are stored in the MySQL database for imagery retrieval. Finally, we introduce the parallel implementation of distributed retrieval of hyperspectral images based on N-FINDR in details, and evaluate the effectiveness and stability of our proposed method through experiments on real datasets.

This paper presents the “monospinner”: a mechanically simple flying vehicle with only one moving part. The vehicle is shown to be controllable in three translational degrees of freedom and two rotational degrees of freedom. The vehicle has a single scalar control input, the thrust magnitude, and is controlled by a cascaded control strategy with an inner attitude controller and an outer position controller. The vehicle design is chosen based on two robustness metrics: the ability to maintain hover under perturbations and the probability of input saturation based on a stochastic model. The resulting mechanical and control designs are experimentally demonstrated, where it is also shown that the vehicle is sufficiently robust to achieve hover after being thrown into the air.