Autonomous 3D exploration with Unmanned Aerial Vehicle (UAV) is increasingly prevalent for environment monitoring without human intervention. In this study, we present a systematic solution towards efficient UAV exploration in 3D environments. Innovatively, a road map is incrementally built and maintained along with the exploration process, which explicitly exhibits the topological structure of the 3D environment. By simplifying the environment, the road map can efficiently provide the information gain and the cost-to-go for a candidate region to be explored, which are two quantities for Next-Best-View (NBV) evaluation, thus prompting the efficiency for NBV determination. In addition, with reference to the global plan queried on the road map, we propose a local planner based on the potential field method that drives the robot to the information-rich area during the navigation process, which further improves the exploration efficiency. The proposed framework and its composed modules are verified in various 3D environments, which exhibits their distinctive features in NBV selection and better performance in improving the exploration efficiency than other methods.

Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers. In this work, we propose a novel dual-agent framework that integrates a reinforcement learning (RL) agent and a deep learning (DL) agent to jointly determine the movement of the US probe based on the real-time US images, in order to mimic the decision-making process of an expert sonographer to achieve autonomous standard view acquisitions in spinal sonography. Moreover, inspired by the nature of US propagation and the characteristics of the spinal anatomy, we introduce a view-specific acoustic shadow reward to utilize the shadow information to implicitly guide the navigation of the probe toward different standard views of the spine. Our method is validated in both quantitative and qualitative experiments in a simulation environment built with US data acquired from 17 volunteers. The average navigation accuracy toward different standard views achieves $5.18mm/5.25^{\circ }$ and $12.87mm/17.49^{\circ }$ in the intra- and inter-subject settings, respectively. The results demonstrate that our method can effectively interpret the US images and navigate the probe to acquire multiple standard views of the spine.

Photoacoustic tomography (PAT) is a newly developed medical imaging modality, which combines the advantages of pure optical imaging and ultrasound imaging, owning both high optical contrast and deep penetration depth. Very recently, PAT is studied in human brain imaging. Nevertheless, while ultrasound waves are passing through the human skull tissues, the strong acoustic attenuation and aberration will happen, which causes photoacoustic signals’ distortion. In this work, we use 180 T1 weighted magnetic resonance imaging (MRI) human brain volumes along with the corresponding magnetic resonance angiography (MRA) brain volumes, and segment them to generate the 2D human brain numerical phantoms for PAT. The numerical phantoms contain six kinds of tissues, which are scalp, skull, white matter, gray matter, blood vessel and cerebrospinal fluid. For every numerical phantom, Monte-Carlo based optical simulation is deployed to obtain the photoacoustic initial pressure based on optical properties of human brain. Then, two different k-wave models are used for the skull-involved acoustic simulation, which are fluid media model and viscoelastic media model. The former one only considers longitudinal wave propagation, and the latter model takes shear wave into consideration. Then, the PA sinograms with skull-induced aberration is taken as the input of U-net, and the skull-stripped ones are regarded as the supervision of U-net to train the network. Experimental result shows that the skull’s acoustic aberration can be effectively alleviated after U-net correction, achieving conspicuous improvement in quality of PAT human brain images reconstructed from the corrected PA signals, which can clearly show the cerebral artery distribution inside the human skull.

The profile estimation for continuum robots is a crucial problem concerning automatically controlling robots. The conventional method is based on the Cosserat rod theory, which is limited by the dependence of the convergence on the initial guess and computational complexity. To tackle these issues, this article proposes a general kinetostatic model to estimate the profile of the tendon-driven continuum robot (TDCR). We first abstract the backbone of the TDCR as an Euler–Bernoulli beam and then derive the spatial beam constraint model of a circular cross-section beam without considering torsion and shear. Next, taking a single-section TDCR as an example, we provide comprehensive modeling, considering the driving tendon tensions, friction, gravity, and external forces. Subsequently, an algorithm based on the chained spatial beam constraint model is proposed to estimate the robot's profile. The method can be generalized to the TDCR with different configurations. Simulations demonstrate the accuracy, computational efficiency, and computational success rate of our method, as well as its advantages over the state-of-the-art. Real-world experiments have also been performed to validate the effectiveness of our method with three different configurations of the TDCR.

Many neurological disorders are characterized by the focal and anatomically definable lesions within the brain parenchyma. Traditional treatment may introduce major trauma in neurosurgery and conventional medical devices can only trace straight trajectories. To overcome these problems, a design and optimization method for a patient-specific concentric tube robot (CTR) satisfying the constraints of anatomy, surgical tasks and follow-the-leader (FTL) deployment is proposed in this paper. CTR is a tentacle like continuum robot that can work inside confined and complex biological chambers with the ability of tracking complex 3D trajectories. It consists of pre-curved superplastic tubes with hollow cavities to accommodate the surgical tools. These merits make the CTR well suitable for minimally invasive surgeries. This paper introduces a design framework that utilizes preoperative MRI data to configure patient-specific CTR for single and multiple tasks with the minimum number of tubes. A constant curvature circular arc model is built to solve the problem of inverse kinematics. Two iterative optimization methods for single and multiple tasks are proposed to optimize the parameters of the CTR. Initial waypoints of the CTR are produced based on the FTL deployment. The waypoints are then refined using a Follow Shape Rapidly-exploring Random Tree algorithm (FSRRT) for cases that the initial configurations of the CTR cannot completely satisfy the FTL deployment. Simulations and experiments are carried out on a human brain model to validate the proposed methods. The parameters of CTR including the entire length, curvature, radius angle, number, diameter, arc length and the waypoints are obtained. The errors of the FTL deployment are found to be within 2.1mm.