System and method for autonomous navigation using visual sparse map

A method for autonomous navigation using a visual sparse map, comprising:

• obtaining the visual sparse map, the visual sparse map comprising a plurality of visual feature points and a plurality of keyframes;
• capturing an image using the visual sensor;
• acquiring, by a processor of the robotic device, a current pose of the robotic device based on the image and the visual sparse map;
• finding, by the processor, a nearest keyframe, wherein the nearest keyframe is one of the plurality of keyframes that is nearest to the current pose of the robotic device;
• finding, by the processor, a target waypoint, wherein the target waypoint is one of the plurality of keyframes that is ahead of the nearest keyframe and has a pre-determined distance to the nearest keyframe;
• computing, by the processor, transition velocity and rotation velocity of the robotic device based on relative location between the robotic device and the target waypoint;
• and
• controlling, by the processor, operation of the robotic device using the computed transition velocity and rotation velocity to achieve autonomous navigation.

A non-transitory computer readable medium storing computer executable code, wherein the computer executable code, when executed at a processor of a robotic device, is configured to:

• obtain the visual sparse map, the visual sparse map comprising a plurality of visual feature points and a plurality of keyframes;
• capture an image using the visual sensor;
• acquire a current pose of the robotic device based on the image and the visual sparse map;
• find a nearest keyframe, wherein the nearest keyframe is one of the plurality of keyframes that is nearest to the current pose of the robotic device;
• find a target waypoint, wherein the target waypoint is one of the plurality of keyframes that is ahead of the nearest keyframe and has a pre-determined distance to the nearest frame;
• compute transition velocity and rotation velocity of the robotic device based on relative location between the robotic device and the target waypoint;
• and
• control operation of the robotic device using the computed transition velocity and rotation velocity to achieve autonomous navigation.