Methods and systems are provided for controlling wheel-legged quadrupedal robots using pose optimization and force control according to quadratic programming (QP) are disclosed. An example robotic system leverages the whole-body motion and the wheel actuation to roll over high obstacles while keeping the wheel torques to navigate the terrain. Wheel traction and balancing is employed for the robot body. Linear rigid body dynamics with wheels are used for real-time balancing control of wheel-legged robots. Further, an effective pose optimization method is implemented for locomotion over steep ramp and stair terrains. The pose optimization solves for optimal poses to enhance stability and enforce collision-fee constraints for the rolling motion over stair terrain.

Methods and systems are provided for controlling wheel-legged quadrupedal robots using pose optimization and force control according to quadratic programming (QP) are disclosed. An example robotic system leverages the whole-body motion and the wheel actuation to roll over high obstacles while keeping the wheel torques to navigate the terrain. Wheel traction and balancing is employed for the robot body. Linear rigid body dynamics with wheels are used for real-time balancing control of wheel-legged robots. Further, an effective pose optimization method is implemented for locomotion over steep ramp and stair terrains. The pose optimization solves for optimal poses to enhance stability and enforce collision-fee constraints for the rolling motion over stair terrain.

Techniques are disclosed for exploiting modern controls, sensors and actuators to realize a novel family of in-line two-wheeled vehicles (Twills) as robots. Each robot has a front-wheel with a substantially horizontal axis of rotation and a substantially vertical steering axis. The front-wheel with its substantially vertical steering axis has a steering-angle that can be sensed by one or more sensors. There is a rear-wheel with a substantially horizontal axis of rotation. A control module stabilizes the roll angle when the robot is in a forward motion as well as when it is substantially or fully stopped. One or both the wheels of the robot may be endowed by a steering motor for steering and a traction motor for providing traction/torque to the wheel.

A system for controlling aircraft flight control surfaces implements a method including: obtaining a control law for the flight control surfaces as a function of flight controls of the aircraft; obtaining measurements of ground speed, true speed, roll angle, pitch angle, angle of attack, sideslip angle and slope angle; performing an estimation of the wind in three dimensions using the measurements obtained; performing an adjustment of the control law for the flight control surfaces, to counter the estimated wind effect and to obtain an adjusted control law for the flight control surfaces, by adding, to the control law, a term for wind compensation comprising a term proportional to the derivative of the wind estimation; and controlling the aircraft by applying the adjusted control law. Thus, the impact of the wind on the aircraft is reduced by digital processing and automatic adjustment of the control of the flight control surfaces.

A computer of an unmanned aerial vehicle (UAV) accesses, from a memory unit, a problem definition comprising cost functions associated with travel of the UAV. The computer causes movement of the UAV based on the cost functions. The computer adjusts one or more of the cost functions during a flight of the UAV. The computer causes further movement of the UAV based on the adjusted one or more of the cost functions.

A computer of an unmanned aerial vehicle (UAV) accesses, from a memory unit, a problem definition comprising cost functions associated with travel of the UAV. The computer causes movement of the UAV based on the cost functions. The computer adjusts one or more of the cost functions during a flight of the UAV. The computer causes further movement of the UAV based on the adjusted one or more of the cost functions.

The learning system SY1 acquires control information output from a control model M by inputting to the control model M environmental information including weather information in at least one of a surrounding environment of an unmanned aerial vehicle P and an environment of a planned flight area of an unmanned aerial vehicle P, and when the unmanned aerial vehicle P takes an action based on the control information, performs reinforcement learning of the control model M using a reward r representing an evaluation of a result of the action.

There is provided a mobile body that includes an imaging unit to capture an image of an environment around the mobile body, an estimation unit to estimate a position of the mobile body on the basis of the image captured by the imaging unit, a calculation unit to calculate the position of the mobile body on the basis of a control command for controlling movement of the mobile body, and a wind information calculation unit to calculate information regarding wind acting on the mobile body on the basis of a first position that is the position of the mobile body, which is estimated by the estimation unit, and a second position that is the position of the mobile body, which is calculated by the calculation unit.

Various embodiments of the present disclosure provide systems and methods for aerial-based firefighting using a suspended autonomous fire extinguisher.

Various embodiments of the present disclosure provide systems and methods for aerial-based firefighting using a suspended autonomous fire extinguisher.