In this paper, our objective is to improve the performance of the existing framework ShuttleNet in predicting badminton shot types and locations by leveraging past strokes. We participated in the CoachAI Badminton Challenge at IJCAI 2023 and achieved significantly better results compared to the baseline. Ultimately, our team achieved the first position in the competition and we made our code available.

Medical image segmentation is one of the important tasks of computer-aided diagnosis in medical image analysis. Since most medical images have the characteristics of blurred boundaries and uneven intensity distribution, through existing segmentation methods, the discontinuity within the target area and the discontinuity of the target boundary are likely to lead to rough or even erroneous boundary delineation. In this paper, we propose a new iterative refined interactive segmentation method for medical images based on agent reinforcement learning, which focuses on the problem of target segmentation boundaries. We model the dynamic process of drawing the target contour in a certain order as a Markov Decision Process (MDP) based on a deep reinforcement learning method. In the dynamic process of continuous interaction between the agent and the image, the agent tracks the boundary point by point in order within a limited length range until the contour of the target is completely drawn. In this process, the agent can quickly improve the segmentation performance by exploring an interactive policy in the image. The method we proposed is simple and effective. At the same time, we evaluate our method on the cardiac MRI scan data set. Experimental results show that our method has a better segmentation effect on the left ventricle in a small number of medical image data sets, especially in terms of segmentation boundaries, this method is better than existing methods. Based on our proposed method, the dynamic generation process of the predicted contour trajectory of the left ventricle will be displayed online at https://github.com/H1997ym/LV-contour-trajectory.

That was the takeaway on Sept. 7, when the Indian Space Research Organisation (ISRO) lost contact with its Vikram lunar lander during an attempt to touch down at the moon's south pole. India was poised to become the fourth nation to ever successfully touch down softly on the lunar regolith, doing so in a place that no other country has previously reached. Though the space agency is still scrambling to revive communication with Vikram -- which has been spotted from lunar orbit -- the unhappy landing sequence seemed like a painful echo of the situation earlier this year, when a private robotic Israeli lander, Beresheet, crashed into our natural satellite. It's all a reminder that, despite the fact that humans landed on the moon many times during the Apollo missions half a century ago, doing so remains a tough business. Of the 30 soft-landing attempts made by space agencies and companies around the world, more than one-third have ended in failure, space journalist Lisa Grossman tweeted.

The team leading NASA's first mission to take a rock sample from the asteroid Bennu has selected four sites for the OSIRIS-REx spacecraft to'tag'. The spacecraft has already mapped the entire Bennu meteor - dubbed the'apocalypse asteroid' - in order to identify the safest and most accessible spots to retrieve a chunk of its surface. Now, the four locations will be studied before the final two sites – a primary and backup – are selected in December, this year. The OSIRIS-REx sample collection is scheduled for the latter half of 2020, and the spacecraft will return the asteroid samples to Earth on September 24, 2023. Osprey is set in a small crater, 66 feet (20 m) in diameter, which is also located in Bennu's equatorial region at 11 degrees north latitude, while Sandpiper is located in the meteor's southern hemisphere, at 47 degrees south latitude Sites: Nightingale is the northern-most site, situated at 56 degrees north latitude on Bennu, while Kingfisher is located in a small crater near Bennu's equator at 11 degrees north latitude The four candidate sample sites on Bennu are designated Nightingale, Kingfisher, Osprey, and Sandpiper – all birds native to Egypt. The naming theme complements the mission's two other naming conventions – Egyptian deities (the asteroid and spacecraft) and mythological birds (surface features on Bennu).

Before you can zip about in a flying car, engineers must solve more than a few problems. Oddly, figuring out how to make a flying car fly isn't among them. The basics of flight were sorted out more than 100 years ago. No, the big challenge lies in making these things fly themselves so you don't have to go through the hassle of earning a pilot's license. "Takeoff is fairly scripted," says Sanjiv Signh, the CEO of Near Earth Autonomy.

Although our skies are now filled with quadcopter drones, fixed-wing aircraft have them beat in both speed and endurance; that's why the military's drones don't look like the ones you'd buy on Amazon. One of the biggest drawbacks with fixed-wing planes is that they tend to require a long runway for landing. However, drone makers are searching for a better way, and it turns out nature solved the problem millions of years ago. Now, we're trying to steal its secret. They can land on a dime by swooping in at low altitude then angling their wings upwards and spreading their feathers to act as air brakes.

Although our skies are now filled with quadcopter drones, fixed-wing aircraft have them beat in both speed and endurance--that's why the military's drones don't look like the ones you'd buy on Amazon. But one of the biggest drawbacks with fixed-wing planes is that they tend to require a long runway for landing. But drone makers are searching for a better way, and it turns out nature solved the problem millions of years ago. Now, we're trying to steal its secret. They can land on a dime by swooping in at low altitude then angling their wings upwards and spreading their feathers to act as air brakes.

Researchers at Stanford University have developed a spider-like drone that can cling to walls and even perch on the ceiling. The versatile drone is equipped with'micro-spines' which create an opposing grip, allowing it to sit on rough, outdoor surfaces. These capabilities have potential applications in the monitoring of typically hard-to-reach areas, and its uses could range anywhere from the detection of damage on bridges to assisting in rescue missions. Researchers at Stanford University have developed a spider-like drone that can cling to walls and even perch on the ceiling. The versatile drone is equipped with'micro-spines' which create an opposing grip, allowing it to sit on rough, outdoor surfaces Micro-spines create two opposing grips, which pull inward to counterbalance the vehicle's movement and provide a grasping force.

Delivery by drone may be legal within two years. Just don't expect many pizzas or packages to wing their way through your neighborhood by then. Despite huge interest in unmanned aerial vehicles (UAVs), and considerable hype around the idea of using them to deliver goods, experts say significant challenges still need to be solved for drone delivery to get off the ground. Google and Amazon are leading the development of delivery drones, while UPS, FedEx, and a host of startups are also researching the technology. Earlier this month, the U.S. Senate Transportation Committee drafted a bill that paves the way for regulation of delivery drones within two years.