Deploying autonomous robots in crowded indoor environments usually requires them to have accurate dynamic obstacle perception. Although plenty of previous works in the autonomous driving field have investigated the 3D object detection problem, the usage of dense point clouds from a heavy LiDAR and their high computation cost for learning-based data processing make those methods not applicable to small robots, such as vision-based UAVs with small onboard computers. To address this issue, we propose a lightweight 3D dynamic obstacle detection and tracking (DODT) method based on an RGB-D camera, which is designed for low-power robots with limited computing power. Our method adopts a novel ensemble detection strategy, combining multiple computationally efficient but low-accuracy detectors to achieve real-time high-accuracy obstacle detection. Besides, we introduce a new feature-based data association method to prevent mismatches and use the Kalman filter with the constant acceleration model to track detected obstacles. In addition, our system includes an optional and auxiliary learning-based module to enhance the obstacle detection range and dynamic obstacle identification. The users can determine whether or not to run this module based on the available computation resources. The proposed method is implemented in a small quadcopter, and the experiments prove that the algorithm can make the robot detect dynamic obstacles and navigate dynamic environments safely.
相關內容
Angiography is widely used to detect, diagnose, and treat cerebrovascular diseases. While numerous techniques have been proposed to segment the vascular network from different imaging modalities, deep learning (DL) has emerged as a promising approach. However, existing DL methods often depend on proprietary datasets and extensive manual annotation. Moreover, the availability of pre-trained networks specifically for medical domains and 3D volumes is limited. To overcome these challenges, we propose a few-shot learning approach called VesselShot for cerebrovascular segmentation. VesselShot leverages knowledge from a few annotated support images and mitigates the scarcity of labeled data and the need for extensive annotation in cerebral blood vessel segmentation. We evaluated the performance of VesselShot using the publicly available TubeTK dataset for the segmentation task, achieving a mean Dice coefficient (DC) of 0.62(0.03).
The occurrence of extreme events like heavy precipitation or storms at a certain location often shows a clustering behaviour and is thus not described well by a Poisson process. We construct a general model for the inter-exceedance times in between such events which combines different candidate models for such behaviour. This allows us to distinguish data generating mechanisms leading to clusters of dependent events with exponential inter-exceedance times in between clusters from independent events with heavy-tailed inter-exceedance times, and even allows us to combine these two mechanisms for better descriptions of such occurrences. We investigate a modification of the Cram\'er-von Mises distance for the purpose of model fitting. An application to mid-latitude winter cyclones illustrates the usefulness of our work.
We aim to efficiently compute spreading speeds of reaction-diffusion-advection (RDA) fronts in divergence free random flows under the Kolmogorov-Petrovsky-Piskunov (KPP) nonlinearity. We study a stochastic interacting particle method (IPM) for the reduced principal eigenvalue (Lyapunov exponent) problem of an associated linear advection-diffusion operator with spatially random coefficients. The Fourier representation of the random advection field and the Feynman-Kac (FK) formula of the principal eigenvalue (Lyapunov exponent) form the foundation of our method implemented as a genetic evolution algorithm. The particles undergo advection-diffusion, and mutation/selection through a fitness function originated in the FK semigroup. We analyze convergence of the algorithm based on operator splitting, present numerical results on representative flows such as 2D cellular flow and 3D Arnold-Beltrami-Childress (ABC) flow under random perturbations. The 2D examples serve as a consistency check with semi-Lagrangian computation. The 3D results demonstrate that IPM, being mesh free and self-adaptive, is simple to implement and efficient for computing front spreading speeds in the advection-dominated regime for high-dimensional random flows on unbounded domains where no truncation is needed.
This paper investigates a swarm of autonomous mobile robots in the Euclidean plane, under the semi-synchronous ($\cal SSYNC$) scheduler. Each robot has a target function to determine a destination point from the robots' positions. All robots in the swarm take the same target function conventionally. We allow the robots to take different target functions, and investigate the effects of the number of distinct target functions on the problem-solving ability, regarding target function as a resource to solve a problem like time. Specifically, we are interested in how many distinct target functions are necessary and sufficient to solve a problem $\Pi$. The number of distinct target functions necessary and sufficient to solve $\Pi$ is called the minimum algorithm size (MAS) for $\Pi$. The MAS is defined to be $\infty$, if $\Pi$ is unsolvable even for the robots with unique target functions. We show that the problems form an infinite hierarchy with respect to their MASs; for each integer $c > 0$ and $\infty$, the set of problems whose MAS is $c$ is not empty, which implies that target function is a resource irreplaceable, e.g., with time. We propose MAS as a natural measure to measure the complexity of a problem. We establish the MASs for solving the gathering and related problems from any initial configuration, i.e., in a self-stabilizing manner. For example, the MAS for the gathering problem is 2. It is 3, for the problem of gathering {\bf all non-faulty} robots at a single point, regardless of the number $(< n)$ of crash failures. It is however $\infty$, for the problem of gathering all robots at a single point, in the presence of at most one crash failure.
The mission of visual brain-computer interfaces (BCIs) is to enhance information transfer rate (ITR) to reach high speed towards real-life communication. Despite notable progress, noninvasive visual BCIs have encountered a plateau in ITRs, leaving it uncertain whether higher ITRs are achievable. In this study, we investigate the information rate limits of the primary visual channel to explore whether we can and how we should build visual BCI with higher information rate. Using information theory, we estimate a maximum achievable ITR of approximately 63 bits per second (bps) with a uniformly-distributed White Noise (WN) stimulus. Based on this discovery, we propose a broadband WN BCI approach that expands the utilization of stimulus bandwidth, in contrast to the current state-of-the-art visual BCI methods based on steady-state visual evoked potentials (SSVEPs). Through experimental validation, our broadband BCI outperforms the SSVEP BCI by an impressive margin of 7 bps, setting a new record of 50 bps. This achievement demonstrates the possibility of decoding 40 classes of noninvasive neural responses within a short duration of only 0.1 seconds. The information-theoretical framework introduced in this study provides valuable insights applicable to all sensory-evoked BCIs, making a significant step towards the development of next-generation human-machine interaction systems.
Many robotic systems locomote using gaits - periodic changes of internal shape, whose mechanical interaction with the robot's environment generate characteristic net displacements. Prominent examples with two shape variables are the low Reynolds number 3-link "Purcell swimmer" with inputs of 2 joint angles and the "ideal fluid" swimmer. Gait analysis of these systems allows for intelligent decisions to be made about the swimmer's locomotive properties, increasing the potential for robotic autonomy. In this work, we present comparative analysis of gait optimization using two different methods. The first method is variational approach of "Pontryagin's maximum principle" (PMP) from optimal control theory. We apply PMP for several variants of 3-link swimmers, with and without incorporation of bounds on joint angles. The second method is differential-geometric analysis of the gaits based on curvature (total Lie bracket) of the local connection for 3-link swimmers. Using optimized body-motion coordinates, contour plots of the curvature in shape space give visualization that enables identifying distance-optimal gaits as zero level sets. Combining and comparing results of the two methods enables better understanding of changes in existence, shape and topology of distance-optimal gait trajectories, depending on the swimmers' parameters.
Evolutionary search-based techniques are commonly used for testing autonomous robotic systems. However, these approaches often rely on computationally expensive simulator-based models for test scenario evaluation. To improve the computational efficiency of the search-based testing, we propose augmenting the evolutionary search (ES) with a reinforcement learning (RL) agent trained using surrogate rewards derived from domain knowledge. In our approach, known as RIGAA (Reinforcement learning Informed Genetic Algorithm for Autonomous systems testing), we first train an RL agent to learn useful constraints of the problem and then use it to produce a certain part of the initial population of the search algorithm. By incorporating an RL agent into the search process, we aim to guide the algorithm towards promising regions of the search space from the start, enabling more efficient exploration of the solution space. We evaluate RIGAA on two case studies: maze generation for an autonomous ant robot and road topology generation for an autonomous vehicle lane keeping assist system. In both case studies, RIGAA converges faster to fitter solutions and produces a better test suite (in terms of average test scenario fitness and diversity). RIGAA also outperforms the state-of-the-art tools for vehicle lane keeping assist system testing, such as AmbieGen and Frenetic.
In many scientific applications the aim is to infer a function which is smooth in some areas, but rough or even discontinuous in other areas of its domain. Such spatially inhomogeneous functions can be modelled in Besov spaces with suitable integrability parameters. In this work we study adaptive Bayesian inference over Besov spaces, in the white noise model from the point of view of rates of contraction, using $p$-exponential priors, which range between Laplace and Gaussian and possess regularity and scaling hyper-parameters. To achieve adaptation, we employ empirical and hierarchical Bayes approaches for tuning these hyper-parameters. Our results show that, while it is known that Gaussian priors can attain the minimax rate only in Besov spaces of spatially homogeneous functions, Laplace priors attain the minimax or nearly the minimax rate in both Besov spaces of spatially homogeneous functions and Besov spaces permitting spatial inhomogeneities.
MultiPA: a multi-task speech pronunciation assessment system for a closed and open response scenario
The design of automatic speech pronunciation assessment can be categorized into closed and open response scenarios, each with strengths and limitations. A system with the ability to function in both scenarios can cater to diverse learning needs and provide a more precise and holistic assessment of pronunciation skills. In this study, we propose a Multi-task Pronunciation Assessment model called MultiPA. MultiPA provides an alternative to Kaldi-based systems in that it has simpler format requirements and better compatibility with other neural network models. Compared with previous open response systems, MultiPA provides a wider range of evaluations, encompassing assessments at both the sentence and word-level. Our experimental results show that MultiPA achieves comparable performance when working in closed response scenarios and maintains more robust performance when directly used for open responses.
Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems. Current approaches designed for hypergraphs, however, are unable to handle different types of hypergraphs and are typically not generic for various learning tasks. Indeed, models that can predict variable-sized heterogeneous hyperedges have not been available. Here we develop a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes. We perform extensive evaluations on multiple datasets, including four benchmark network datasets and two single-cell Hi-C datasets in genomics. We demonstrate that Hyper-SAGNN significantly outperforms the state-of-the-art methods on traditional tasks while also achieving great performance on a new task called outsider identification. Hyper-SAGNN will be useful for graph representation learning to uncover complex higher-order interactions in different applications.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191