Abstract: Presented herein are embodiments of a two-stage methodology that integrates data-driven imitation learning and model-based trajectory optimization to generate optimal trajectories for autonomous excavators. In one or more embodiments, a deep neural network using demonstration data to mimic the operation patterns of human experts under various terrain states, including their geometry shape and material type. A stochastic trajectory optimization methodology is used to improve the trajectory generated by the neural network to ensure kinematics feasibility, improve smoothness, satisfy hard constraints, and achieve desired excavation volumes. Embodiments were tested on a Franka robot arm equipped with a bucket end-effector. Embodiments were also evaluated on different material types, such as sand and rigid blocks. Experimental results showed that embodiments of the two-stage methodology that comprises combining expert knowledge and model optimization increased the excavation weights by up to 24.

Abstract: A tracer particle spreading device for a boundary layer flow visualization experiment based on a flat plate includes a tracer particle generator, a smoke storage box, and a wall-surface particle distribution box. Fume and oil are pressurized by a micro pump and flows into a heating pipe to be heated and vaporized, and then is ejected from a nozzle to form tracer particles. The tracer particles enter the smoke storage box via a smoke guiding tube. An axial flow fan is mounted on a wall surface of the smoke storage box. The tracer particles enter a cavity of the wall-surface particle distribution box via the smoke guiding tube, and the tracer particles are rectified by a rectifying plate and ejected from a spreading slit. An outlet of the spreading slit is at an angle of 15° with respect to an experiment flat plate.

Abstract: Autonomous excavator has developed rapidly in recent years because of a shortage of labor and hazardous working environments for operating excavators. Presented herein are embodiments of a novel hierarchical planning system for autonomous machines, such as excavators. In one or more embodiments, the overall planning system comprises a high-level task planner for task division and base movement planning, and general sub-task planners with motion primitives, which include both arm and base movement in the case of an excavator. Using embodiments of the system architecture, experiments were performed for the trench and pile removal tasks in the real world and for the large-scale material loading tasks in a simulation environment. The results show that the system architecture embodiments and planner method embodiments generate effective task and motion plans that perform well in autonomous excavation.

Abstract: The disclosure provides a micro-groove drag reduction flexible film and a preparation method thereof. The micro-groove film has a triangular groove structure on the upper surface along the direction of an air flow, and an adhesive layer on the lower surface for quick adhesion to an aircraft surface. After the surface of the aircraft is covered with a micro-groove film, it could limit the spanwise movement of the bottom air at the boundary layer of the aircraft surface, improve the flow field characteristics of the aircraft near the wall, and effectively reduce the frictional resistance of the wall. The micro-groove flexible film is prepared by a roller hot pressing method. The triangular groove structure is processed on the surface of the mold roller of the double roller hot press. After pretreatment of the thermoplastic polyurethane (TPU) polymer film, a micro-groove structure is hot-pressed on the surface of the TPU film.

Abstract: A tracer particle spreading device for a boundary layer flow visualization experiment based on a flat plate includes a tracer particle generator, a smoke storage box, and a wall-surface particle distribution box. Fume and oil are pressurized by a micro pump and flows into a heating pipe to be heated and vaporized, and then is ejected from a nozzle to form tracer particles. The tracer particles enter the smoke storage box via a smoke guiding tube. An axial flow fan is mounted on a wall surface of the smoke storage box. The tracer particles enter a cavity of the wall-surface particle distribution box via the smoke guiding tube, and the tracer particles are rectified by a rectifying plate and ejected from a spreading slit. An outlet of the spreading slit is at an angle of 15° with respect to an experiment flat plate.

Abstract: A dragonfly-like miniature four-winged ornithopter includes: a fuselage (101), two front flapping wings (102), two front wing connectors (103) with first connecting rods, two rear flapping wings (104), two rear wing connectors (105) with second connecting rods, a driving gear (106), a shaft gear (107), a first-stage gear (108), two second-stage gears (109) with third connecting rods, two third-stage gears (114) with fourth connecting rods, two front ball joint connecting rods (110), two rear ball joint connecting rods (111), two steering engine connecting rods (112), two steer engines (113), and a brushless direct current motor.

Abstract: The present disclosure discloses an energy management system suitable for a solar-powered unmanned aerial vehicle and a control method thereof, which are used for an aerospace vehicle energy system. The system comprises a photovoltaic module, an MPPT controller, a first DC-DC circuit, a battery pack, a first anti-reverse circuit, a second DC-DC circuit, a second anti-reverse circuit, an ESC, a BLDC, an on-board controller, a communication link and a voltage stabilizing module. During cruising, the battery pack directly supplies power to the ESC through the first anti-reverse circuit; when high-power power output is needed, the battery pack supplies power to the ESC through the second DC-DC circuit and the second anti-reverse circuit in sequence, wherein the output voltage of the second DC-DC circuit and the accelerator signal input of the ESC are controlled by the on-board controller.

Abstract: The present disclosure discloses an energy management system suitable for a solar-powered unmanned aerial vehicle and a control method thereof, which are used for an aerospace vehicle energy system. The system comprises a photovoltaic module, an MPPT controller, a first DC-DC circuit, a battery pack, a first anti-reverse circuit, a second DC-DC circuit, a second anti-reverse circuit, an ESC, a BLDC, an on-board controller, a communication link and a voltage stabilizing module. During cruising, the battery pack directly supplies power to the ESC through the first anti-reverse circuit; when high-power power output is needed, the battery pack supplies power to the ESC through the second DC-DC circuit and the second anti-reverse circuit in sequence, wherein the output voltage of the second DC-DC circuit and the accelerator signal input of the ESC are controlled by the on-board controller.

Abstract: The present disclosure provides an efficient control system and method for a brushless motor with a wide working range, which are applied to an aerospace vehicle energy system. The system of the present disclosure includes a power supplying module, a first DC-DC circuit, a battery pack, a second DC-DC circuit, an anti-reverse-connection circuit, an electronic speed control (ESC), a brushless direct current motor (BLDC), an airborne controller and a communication link. Electric energy from the power supplying module is configured to charge the battery pack via the first DC-DC circuit, and electric energy of the battery pack sequentially flows through the second DC-DC circuit and the anti-reverse-connection circuit to energize the ESC, wherein output voltage of the second DC-DC circuit and throttle signal input of the ESC are controlled in real time by the airborne controller according to a power demand of an aircraft.

Abstract: The present disclosure provides an efficient control system and method for a brushless motor with a wide working range, which are applied to an aerospace vehicle energy system. The system of the present disclosure includes a power supplying module, a first DC-DC circuit, a battery pack, a second DC-DC circuit, an anti-reverse-connection circuit, an electronic speed control (ESC), a brushless direct current motor (BLDC), an airborne controller and a communication link. Electric energy from the power supplying module is configured to charge the battery pack via the first DC-DC circuit, and electric energy of the battery pack sequentially flows through the second DC-DC circuit and the anti-reverse-connection circuit to energize the ESC, wherein output voltage of the second DC-DC circuit and throttle signal input of the ESC are controlled in real time by the airborne controller according to a power demand of an aircraft.