Search

In the field of monocular depth estimation (MDE), many models with excellent zero-shot performance in general scenes emerge recently. However, these methods often fail in predicting non-Lambertian surfaces, such as transparent or mirror (ToM) surfaces, due to the unique reflective properties of these regions. Previous methods utilize externally provided ToM masks and aim to obtain correct depth maps through direct in-painting of RGB images. These methods highly depend on the accuracy of additional input masks, and the use of random colors during in-painting makes them insufficiently robust. We are committed to incrementally enabling the baseline model to directly learn the uniqueness of non-Lambertian surface regions for depth estimation through a well-designed training framework. Therefore, we propose non-Lambertian surface regional guidance, which constrains the predictions of MDE model from the gradient domain to enhance its robustness. Noting the significant impact of lighting on this task, we employ the random tone-mapping augmentation during training to ensure the network can predict correct results for varying lighting inputs. Additionally, we propose an optional novel lighting fusion module, which uses Variational Autoencoders to fuse multiple images and obtain the most advantageous input RGB image for depth estimation when multi-exposure images are available. Our method achieves accuracy improvements of 33.39% and 5.21% in zero-shot testing on the Booster and Mirror3D dataset for non-Lambertian surfaces, respectively, compared to the Depth Anything V2. The state-of-the-art performance of 90.75 in delta1.05 within the ToM regions on the TRICKY2024 competition test set demonstrates the effectiveness of our approach.

The conditional diffusion model has been demonstrated as an efficient tool for learning robot policies, owing to its advancement to accurately model the conditional distribution of policies. The intricate nature of real-world scenarios, characterized by dynamic obstacles and maze-like structures, underscores the complexity of robot local navigation decision-making as a conditional distribution problem. Nevertheless, leveraging the diffusion model for robot local navigation is not trivial and encounters several under-explored challenges: (1) Data Urgency. The complex conditional distribution in local navigation needs training data to include diverse policy in diverse real-world scenarios; (2) Myopic Observation. Due to the diversity of the perception scenarios, diffusion decisions based on the local perspective of robots may prove suboptimal for completing the entire task, as they often lack foresight. In certain scenarios requiring detours, the robot may become trapped. To address these issues, our approach begins with an exploration of a diverse data generation mechanism that encompasses multiple agents exhibiting distinct preferences through target selection informed by integrated global-local insights. Then, based on this diverse training data, a diffusion agent is obtained, capable of excellent collision avoidance in diverse scenarios. Subsequently, we augment our Local Diffusion Planner, also known as LDP by incorporating global observations in a lightweight manner. This enhancement broadens the observational scope of LDP, effectively mitigating the risk of becoming ensnared in local optima and promoting more robust navigational decisions., Comment: 8 pages, 6 figures, accepted by IROS 2024

As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a degraded performance on the challenging scenarios, mainly because these scenarios appear less frequently in the training data. To address such a long-tail issue, existing methods force challenging scenarios closer together in the feature space during training to trigger information sharing among them for more robust learning. These methods, however, primarily rely on the motion patterns to characterize scenarios, omitting more informative contextual information, such as interactions and scene layout. We argue that exploiting such information not only improves prediction accuracy but also scene compliance of the generated trajectories. In this paper, we propose to incorporate richer training dynamics information into a prototypical contrastive learning framework. More specifically, we propose a two-stage process. First, we generate rich contextual features using a baseline encoder-decoder framework. These features are split into clusters based on the model's output errors, using the training dynamics information, and a prototype is computed within each cluster. Second, we retrain the model using the prototypes in a contrastive learning framework. We conduct empirical evaluations of our approach using two large-scale naturalistic datasets and show that our method achieves state-of-the-art performance by improving accuracy and scene compliance on the long-tail samples. Furthermore, we perform experiments on a subset of the clusters to highlight the additional benefit of our approach in reducing training bias., Comment: 2024 IEEE Intelligent Vehicles Symposium (IV)

This paper applies the UAV to the inspection of water diversion pipelines in hydropower stations. The diversion pipeline is an enclosed space, so the airflow disturbance caused by the rotation of the UAV blades and the strong air convection from the chimney effect have a great impact on the flight control of the UAV. Although the traditional linear control PID flight control algorithm has been widely used and can meet the requirements of general flight tasks, it cannot guarantee the stability of the system over a wide range. The inspection of a diversion line in an enclosed space requires high system stability and robustness of the UAV controller. In this paper, a hybrid stabilised adaptive backstepping control method is proposed. Firstly, a multi-rotor UAV model is analysed and transformed into a strict feedback form with external disturbances; then adaptive techniques are used to estimate the airflow disturbances caused by the blades, and the attitude and position tracking controllers are designed by combining backstepping control and PID control respectively; finally, the asymptotic stability of the system is ensured by constructing a Lyapunov function. The experimental data show that the flight controller designed in this paper has good robustness and tracking performance, and can better resist the disturbance caused by airflow disturbance in confined space., Comment: 7 pages

Recently, the field of Metal-Insulator-Transition (MIT) materials has emerged as an unconventional solution for novel energy efficient electronic functions, such as steep slope subthermionic switches, neuromorphic hardware, reconfigurable radiofrequency functions, new types of sensors, teraherz and optoelectronic devices. Designing radiofrequency (RF) electronic circuits with a MIT material like vanadium dioxide, VO2, requires the understanding of its physics and appropriate models and tools, with predictive capability over large range of frequency (1-100GHz). Here, we develop 3D Smith charts for devices and circuits having complex frequency dependences, like the ones resulting by the use of MIT materials. The novel foundation of a 3D Smith chart involves here the geometrical fundamental notions of oriented curvature and variable homothety in order to clarify first theoretical inconsistencies in Foster and Non Foster circuits, where the driving point impedances exhibit mixed clockwise and counter-clockwise frequency dependent paths on the Smith chart as frequency increases. We show here the unique visualization capability of a 3D Smith chart, which allows to quantify orientation over variable frequency. The new 3D Smith chart is applied as a 3D multi-parameter modelling and design environment for the complex case of Metal-Insulator-Transition (MIT) materials where their permittivity is dependent on the frequency. In this work, we apply 3D Smith charts to on Vanadium Dioxide (VO2) reconfigurable Peano inductors. We report fabricated inductors with record quality factors using VO2 phase transition to program multiple tuning states, operating in the range 4 GHz to 10 GHz. Finally, we fabricate new Peano curves filters used to extract the frequency-dependent dielectric constant of VO2 within 1 GHz-50 GHz for the accurate design of RF electronic applications with phase change materials, Comment: 36 pages, 13 article pages, 23 supplementary pages, 5 main article figures, 32 additional figures

This paper presents the latest observations from the newly-built solar radio spectrograph at the \emph{Chashan Solar Observatory}. On July 18 2016, the spectrograph records a solar spike burst event, which has several episodes showing harmonic structures, with the second, third, and fourth harmonics. The lower harmonic radio spike emissions are observed later than the higher harmonic bands, and the temporal delay of the second (third) harmonic relative to the fourth harmonic is about 30\ --\ 40 (10) ms. Based on the electron cyclotron maser emission mechanism, we analyze possible causes of the temporal delay and further infer relevant coronal parameters, such as the magnetic field strength and the electron density at the radio source., Comment: 17 pages,6 figures