Systems and methods for performing high-speed geofencing in accordance with various embodiments of the invention are disclosed. One embodiment includes a robotics platform including a set of one or more motors, at least one sensor, a controller comprising a set of one or more processors, and a memory containing a controller application and a backup controller application, wherein the controller application configures the set of processors to control the robotics platform by performing the steps of receiving user commands, generating commands controlling the set of one or more motors based on the received commands. The backup controller application configures the set of processors to monitor the controller and intervene as the commands received by the controller direct the robotics platform towards a boundary by performing the steps of defining a safe set identifying positions where the robotics platform is safe, defining an invariant safe set based upon a backup set, where the invariant safe set is a subset of the safe set, and the backup set is a subset of both the invariant safe set and the safe set, receiving commands controlling the set of one or more motors to track to a desired velocity, determining if the robotic platform is approaching, and upon a determination that the robotics platform is approaching a boundary of the invariant safe set, switching control of the motors from the received commands to a combination of the received commands and backup controls generated by the backup controller application.

A golf support system supports a user to play golf on a golf course. The golf support system includes a course travelling vehicle to be operated in the golf course. A photographing unit photographs a trajectory of a golf ball as a trajectory image by using a camera mounted on the course travelling vehicle. A trajectory prediction unit calculates the trajectory of the golf ball as a predicted trajectory by using the trajectory image. A route calculation unit calculates a predicted drop position being a drop position of the golf ball by using the predicted trajectory. Then, the route calculation unit calculates a travelling route to the predicted drop position of the golf ball.

A method for obtaining an exercise video may be disclosed. According to an embodiment of the present invention, the method may comprises the steps of: receiving a first value for specifying a flight height of a drone, a second value for specifying a distance between a first sensor of the drone and a first point on a surface of a first athlete, and a third value for specifying an angular displacement of the drone in a direction from the first point toward the first sensor with respect to a front direction of the first athlete, confirming information that the drone is at the same height as the first value and obtaining video data obtained by a measurement value of at least one sensor of the drone and the first sensor.

Detection of a launch event of an autonomous vehicle may consider input from a variety of sensors, including acceleration sensors and touch sensors In some aspects, a method includes receiving a first input from a touch sensor, receiving a second input from an accelerometer, determining whether a launch of the autonomous vehicle is detected based on the first input and the second input, and controlling the autonomous vehicle in response to the determining. In some aspects, when a launch is detected, a motor of the autonomous vehicle may be energized. By detecting a launch event in this manner, improved safety and reliability may be realized. A reduced occurrence of false positive launch events may reduce a risk that the motor of the autonomous vehicle is energized when the vehicle has not actually been launched.

A robotic athletic training system may include a mobile robotic platform, a sensor module associated with the mobile robotic platform and configured to obtain data from an environment. The system may include a drive system that propels the platform, as well as a steering system that steers the platform. The system may include a processor which receives data from the sensor module and control the drive system or steering system to follow a path based on the data received from the sensor module. A method may include controlling a robotic athletic training system (or robotic training platform) so that it moves at a velocity. The robotic athletic training system may include a vision system configured to receive data related to a surface and compare a baseline data of a desired surface to the received data and adjusting a travel direction of the robotic system in response to the comparison.

The present disclosure discloses a tennis ball-picking robot, including a chassis assembly, a ball-entering control element group, and a ball-collecting mechanism, the ball-entering control element group being disposed on a front end of the chassis assembly and the ball-collecting mechanism being disposed on a rear side of the chassis assembly. The tennis ball-picking robot incorporates multiple AI technologies such as computer vision, simultaneous localization and mapping, and robotics kinematics, enabling intelligent following, mapping and localization, and path planning. The robot can efficiently collect the tennis balls dropped on the court, and the players can also select a ball-picking area and a ball-picking speed pattern of the robot through an APP, improving the ball-picking efficiency, avoiding consuming the physical power of the players due to manual picking, improving the training effect by ultimately ensuring their focus during training, and reducing the training cost.

An information processing apparatus according to an embodiment of the present disclosure includes a control unit that controls automatic following with respect to a target in a shooting region for a visible image to cause the target located in a position corresponding to a characteristic temperature distribution included in thermographic image data to be included in the shooting region. The thermographic image data is data obtained by shooting an image in response to a command to start the automatic following.

A system in accordance with present embodiments includes a ground controller and an unmanned aerial vehicle including communications circuitry configured to transmit signals to and receive signals from the ground controller. The system may also include a vehicle controller configured to execute a flight plan and at least one special effects module. The system may also include a special effects module controller configured to cause the special effect to be activated in response to an activation signal from the ground controller.

The present relates to a method for operating a drone (1) navigating within an arena (18) delimited by boundaries (19), the navigation of the drone (1) in the arena (18) being ruled by a navigation program setting the navigation parameters of the drone (1) to ensure the drone (1) follows a calculated trajectory. The setting of the navigation parameters of the drone (1) in the navigation program depends on the object impacting the drone (1). The setting step comprises implementing a virtual impact setup in the navigation program for adjusting the navigation parameters of the drone (1) to an impact between the drone (1) and a virtual object, and implementing a real impact setup in the navigation program for adjusting the navigation parameters of the drone (1) to an impact between the drone (1) and a physical object.

Disclosed is an intelligent learning and adjustment system for a tennis training robot, including an image recognition system, an algorithm model, a back-end processing platform, and an optimization model. Preprocessing of incoming ball data is performed, various necessary data, such as speeds and directions of flying tennis balls, spinning and placements, are collected, various data sets are processed by using various machine learning algorithms, effective predictions and decisions are generated to facilitate the prediction of the placement and difficulty level of the incoming ball, so that a capability and level of a sparring athlete can be evaluated, the tennis training robot accordingly makes prediction and recognition, and carries out interactive feedback actions in a timely manner. The entire training process involves continuously updating of weights and bias values to make the predictions increasingly accurate, and the tennis training robot can provide an interactive intelligent training method.