A method in accordance with at least some embodiments of the present technology includes determining first hazard information about a human in an environment at a first time. The method further includes decelerating a mobile robot in the environment based at least partially on the first hazard information. The method further includes determining second hazard information about the human at a second time after the first time. The method further includes reconfiguring the mobile robot based at least partially on the second hazard information. Reconfiguring the mobile robot includes moving the mobile robot from a standing configuration to a non-standing configuration. The method further includes determining third hazard information about the human at a third time after the second time. Finally, the method includes causing a safe operating stop of the mobile robot based at least partially on the third hazard information.

A method in accordance with at least some embodiments of the present technology includes determining first hazard information about a human in an environment at a first time. The method further includes decelerating a mobile robot in the environment based at least partially on the first hazard information. The method further includes determining second hazard information about the human at a second time after the first time. The method further includes reconfiguring the mobile robot based at least partially on the second hazard information. Reconfiguring the mobile robot includes moving the mobile robot from a standing configuration to a non-standing configuration. The method further includes determining third hazard information about the human at a third time after the second time. Finally, the method includes causing a safe operating stop of the mobile robot based at least partially on the third hazard information.

A robot step control method, a robot control apparatus, and a storage medium are provided. The method includes: determining an expected support force of two legs of a biped robot according to zero-moment point planning data and actual position data of the two legs at a current moment, and determining a current desired joint posture angle of ankle joints of the two legs and a desired joint position matching an actual leg support state using a compliance control algorithm based on an expected support force of the two legs, and centroid movement planning data, centroid actual movement data, step planning data and actual force data of the two legs at the current moment. In such manner, all-direction compliant controls can be performed on a desired leg pose condition according to the actual motion status of the biped robot, thereby improving the walking stability and terrain adaptability of the biped robot.

A posture control method is a posture control method of a non-linear inverted pendulum model, of which a height of a center of gravity is variable, and a trajectory of the center of gravity is an energy conserving system, using a control device, the posture control method including: obtaining a conservation energy function on the basis of a measured value of the center of gravity; converting the conservation energy function into a curve function; and calculating a set of eigenvectors through approximation as a convergent component and a divergent component without iterative calculation of a controllable area in a phase plot of the converted curve function and feeding back the convergent component and the divergent component that have been calculated.

A system and method for providing a position and rate of change for a robot that is useful in a robotic control system. The invention uses an inverted pendulum and flywheel model. The model produces a linear momentum parameter and an angular momentum parameter. The inventors have developed a modified velocity measure for the control system that combines both the linear and angular rates of motion for the robot into an equivalent linear rate. This equivalent linear rate captured the same dynamic effects as using both a linear and angular rate does for the prior art systems. The developed equivalent linear rate can be used for a number of purposes, including feedback control during walking, step placement, planning, and measurement of balance conditions.

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.

Various implementations are provided which include receiving an instance of natural language (NL) text input indicating a task for a multi-legged robot to perform in an environment. In many implementations, the system can process the NL text input using a large language model (LLM) to generate a foot contact pattern, indicating a sequence of leg positions of the robot relative to the surface, where one or more of the legs of the robot are in contact with the surface. Additionally or alternatively, the system can generate low-level robot control output by processing the foot contact pattern using a locomotion controller.

A robot traveling method, includes: detecting an obstacle, and obtaining first coordinate points of the obstacle in a first coordinate system which is a coordinate system of an obstacle detector; obtaining second coordinate points of the obstacle in a second coordinate system by performing coordinate system transformation on the first coordinate points, the second coordinate system being a coordinate system of a robot; obtaining a first azimuth corresponding to each second coordinate point, traversing all the first azimuths, and determining a farthest target coordinate point that the robot is allowed to reach when walking along a currently traversed first azimuth by performing coordinate axis rotation on all the second coordinate points based on the currently traversed first azimuth; and obtaining a target azimuth deviation of the robot based on the target coordinate point corresponding to each first azimuth, and controlling the robot to travel based on the target azimuth deviation.

The invention is notably directed to a computer-implemented method of operating a legged robot. The method repeatedly performs algorithmic cycles at the robot. Each cycle comprises updating a state of the robot as well as heterogeneous representations (321, 322, 323) of an environment of the robot based on signals from a set of sensors. The heterogeneous representations are of different kinds and/or dimensions and, therefore, represent different contents or, at the very least, represent them in different ways. They include a first representation (321), such as a spherical ego-centric map, and a second representation (322), such as an obstacle map. Next, the method generates an initial trajectory that avoids obstacles in the first representation. The initial trajectory is generated through a first model (2061) based on the first representation (321) and the robot's state as updated last, where the first model is a computational model that has been trained in reinforcement learning. The method subsequently executes a second model (2062) based on the initial trajectory, as well as the state of the robot and the second representation as updated last, to obtain a collision-free trajectory. A third representation (323), such as an elevation map, may be used by a low-level policy (208) to generate low-level commands. The robot is eventually controlled according to the low-level commands generated to cause a legged locomotion of the robot. The invention is further directed to related systems and computer program products.

Disclosed herein are methods, devices, systems, and computer programs stored on computer-readable media for managing navigation in autonomous systems. One method includes: determining a route for navigation, communicating with a navigation managing system to determine whether a terrain map for the route is available, and in response to a determination that the terrain map is unavailable at the navigation managing system, navigating the route and generating the terrain map.