9results about How to "Improve mission performance" patented technology

The application relates to a laser radar SLAM and vegetation feature library matching method and system of a mowing robot, and relates to the technical field of data processing. The method comprises the following steps: determining initial laser radar parameters based on laser radar test data of a plurality of sample vegetation; establishing a vegetation feature library based on the initial laser radar parameters and the laser radar test data of the plurality of sample vegetation; determining environmental influence factors based on the initial laser radar parameters; acquiring real-time environmental information of the mowing robot; adjusting the initial laser radar parameters based on the environmental influence factors and the real-time environmental information to generate current laser radar parameters; acquiring point clouds of vegetation to be matched based on the current laser radar parameters; determining a vegetation type based on the point clouds of the vegetation to be matched and the vegetation feature library; and updating a two-dimensional grid map or a three-dimensional point cloud map of an environment where the mowing robot is located based on the point clouds of the vegetation to be matched and the vegetation type, so that the intelligent level of the mowing robot is improved.

The application belongs to the technical field of artificial intelligence and relates to a role large model personality and task linkage ability enhancement method and related products. According to user input natural language task instructions and personality setting information, a role large model generates a subtask sequence and an ability requirement set. For each subtask, if the subtask and the corresponding target ability match the personality setting information, the role large model calls the target ability to execute the subtask to obtain a subtask result. If the subtask and the target ability do not match, the subtask and the target ability are subjected to personality adaptation reconstruction before execution to obtain a subtask result. According to the personality setting information, the subtask result is subjected to personality polishing to obtain a personalized subtask result. The personalized subtask results are integrated in sequence into a complete task result, which is subjected to personality polishing again to obtain a personalized complete task result that is output to the user. The application can improve the task execution ability of the role large model while maintaining personality consistency.

The robot dog with the multiple mechanical arms comprises a robot dog body, a multi-mode moving module is integrated at the bottom of the robot dog body, a mechanical arm butt joint rail is arranged on the upper side of the edge of the robot dog body, and at least two standardized power connection butt joint bases are arranged on the mechanical arm butt joint rail. A mechanical arm connecting base is fixedly connected to the front face of the power connection butt joint base in an inserted mode, an operation mechanical arm module is arranged on the front side of the mechanical arm connecting base, a modularized tail end claw is detachably installed at the tail end of the operation mechanical arm module, and the operation mechanical arm module and the modularized tail end claw are driven by a servo motor or hydraulically to operate. And through the arranged mechanical arm butt joint rail and the power connection butt joint bases, different numbers of power connection butt joint bases can be installed according to task requirements, and the number of the operation mechanical arm modules is flexibly adjusted so as to adapt to the task requirements of different scenes. Multi-task synchronous execution is realized, and the rescue efficiency is greatly improved.

The invention provides a computing resource dynamic scheduling method and device, equipment and a medium. The method comprises the steps of obtaining a task feature vector of at least one target model training task; obtaining a computing device computing resource vector provided by a resource awareness twin network, wherein the resource awareness twin network is constructed based on computing capabilities of various computing devices; obtaining a candidate computing device set according to the similarity between the task feature vector and the computing device computing resource vector; determining a task allocation scheme for allocating the at least one target model training task to computing equipment in the candidate computing equipment set according to the completion time of the at least one target model training task and target computing resources of the candidate computing equipment set; and dynamically scheduling the at least one target model training task according to the task allocation scheme. According to the method, the overall utilization efficiency and the task execution efficiency of heterogeneous computing power resources are improved.

The invention provides a robot control method and device and a robot, and is applied to the technical field of robots. Performing target detection on the visual image to obtain a candidate image area, and screening masks in the candidate image area; determining three-dimensional observation information in the candidate image area based on the screened mask, and aligning the three-dimensional observation information with a CAD model matched with the target object to obtain pose information of the target object; according to the pose information and the identifier of the CAD model, determining a hand grabbing pose of the robot from a preset hand pose database; according to the method, the robot is subjected to hand posture control according to the hand grabbing posture, object posture estimation is conducted by combining the three-dimensional observation information and the CAD model, then the hand grabbing posture is determined, hand posture control is conducted on the robot, the precision and efficiency of the robot for executing body grabbing are improved, and then the task execution effect is improved.

This invention relates to the field of computing power scheduling technology, specifically to an AI computing power scheduling method and system for private large-scale models. The invention performs attention encoding on multi-source heterogeneous data to obtain format recognition results and acquisition priority labels; generates a memory pressure pre-transmission signal based on the format recognition results; extracts structural features from high-quality data streams and generates computing power affinity encoding vectors through graph neural networks; constructs a state space combined with a secure computing power pre-occupancy mechanism, outputting a resource allocation action sequence; further performs memory oversubscription, core binding, NUMA node crossing, and network bandwidth conflict detection, and resolves conflicts and performs affinity rearrangement based on task priorities to generate a conflict-free instruction sequence. This invention can improve the utilization efficiency of heterogeneous computing power resources, reduce the probability of resource conflicts, and improve the scheduling stability and execution efficiency during the training and inference process of private large-scale models.

The invention discloses a hardware acceleration path selection method, electronic equipment and a storage medium, and the method comprises the steps: carrying out the feature extraction of a target processing task under the condition of receiving the target processing task, and obtaining a task feature vector corresponding to the target processing task; acquiring a hardware capability vector corresponding to each hardware acceleration resource, wherein the dimension of the hardware capability vector corresponds to the dimension of the task feature vector; matching the task feature vector corresponding to the target processing task with the hardware capability vector corresponding to each hardware acceleration resource to obtain the matching degree of each hardware acceleration resource to the target processing task; and according to the matching degree of each hardware acceleration resource to the target processing task, selecting target hardware for executing the target processing task from each hardware acceleration resource.

The application provides a spatiotemporal tensor task priority local planning method for unmanned surface vehicle, and belongs to the technical field of autonomous unmanned system navigation and control, and comprises the following steps: constructing a unified three-dimensional spatiotemporal tensor based on environment perception data; the three-dimensional spatiotemporal tensor integrally encodes static obstacle information and future prediction occupation information of dynamic obstacles, supports constant time complexity collision feasibility query of any position and time combination; generating guidance reference information containing expected heading based on time parameterized reference trajectory; generating a candidate control action set based on the current motion state, performing collision constraint verification on the candidate control action based on the three-dimensional spatiotemporal tensor, screening to obtain a safe action set satisfying the non-collision constraint, and selecting an optimal control action in the safe action set with the only optimization target of minimizing the deviation between the predicted ship heading and the expected heading; and step four, generating a local planning path based on the optimal control action, and controlling the unmanned surface vehicle to sail.

The application relates to the technical field of underwater vehicles and provides a submersible energy management method and system based on a demand distribution strategy, which comprises the following steps: obtaining historical data of a submersible performing a task, wherein the historical data comprises task demand data and energy consumption data; constructing an initial task energy consumption model; training and verifying the initial task energy consumption model according to the task demand data and the energy consumption data to obtain a task energy consumption model; obtaining task target data of the submersible to be executed; dividing the task to be executed of the submersible into multiple subtasks to be executed according to the task target data to be executed; obtaining subtask demand data of the subtasks to be executed; obtaining energy consumption data of the subtasks to be executed through the task energy consumption model and the subtask demand data; evaluating the priority of the subtasks to be executed according to the subtask demand data; and performing energy distribution on the subtasks to be executed based on an energy distribution strategy, the priority and the energy consumption data of the subtasks to be executed.