Information processing apparatus, information processing method, program, and flight object
To enable high-speed autonomous flight of a flight object. A three-dimensional real-time observation result is generated on the basis of self-position estimation information and three-dimensional distance measurement information. A prior map corresponding to a three-dimensional real-time observation result is acquired. The three-dimensional real-time observation result and the prior map are aligned. After the alignment, the three-dimensional real-time observation result is expanded on the basis of the prior map. A flight route is set on the basis of the three-dimensional real-time observation result having been expanded. In the flight object such as a drone, a somewhat long flight route can be accurately calculated at a time in a global behavior plan, which enables high-speed autonomous flight of the flight object.
1 . An information processing apparatus comprising:
circuitry configured to
generate a three-dimensional real-time observation result based on self-position estimation information and three-dimensional distance measurement information obtained from a sensor,
acquire a prior map corresponding to the three-dimensional real-time observation result,
align the three-dimensional real-time observation result with the prior map,
expand the three-dimensional real-time observation result based on the prior map, and
determine a flight route based on the three-dimensional real-time observation result having been expanded,
wherein the prior map includes information related to recognized environmental structure including at least one of a topography, a wall, or a building,
wherein the circuitry is further configured to expand the three-dimensional real-time observation result corresponding to semantic segmentation of the recognized environmental structure so that an expanded area of the three-dimensional real-time result is continuous for same semantics within and outside a detection range of the sensor, and
wherein the circuitry is further configured to
perform the semantic segmentation on the three-dimensional real-time observation result to determine whether continuity is present in semantics at a connection portion with respect to previously performed semantic segmentation of the prior map in relation to the recognized environmental structure, and
expand, with a result of the semantic segmentation, a plane at the connection portion.
2 . The information processing apparatus according to claim 1 ,
wherein the circuitry is configured to expand the three-dimensional real-time observation result in an unobservable area.
3 . The information processing apparatus according to claim 1 ,
wherein the circuitry is further configured to
perform plane detection on the three-dimensional real-time observation result, and
expand, with a result of the plane detection, the plane based on information regarding the prior map.
4 . The information processing apparatus according to claim 1 ,
wherein the three-dimensional real-time observation result corresponds to a three-dimensional occupancy grid map.
5 . The information processing apparatus according to claim 1 ,
wherein the circuitry is configured to acquire the prior map from a different information processing apparatus through communication.
6 . The information processing apparatus according to claim 5 ,
wherein the prior map corresponds to a map based on the three-dimensional real-time observation result generated by the different information processing apparatus.
7 . The information processing apparatus according to claim 1 ,
wherein the prior map corresponds to a map obtained by processing of cutting the three-dimensional real-time observation result at a certain height and converting the cut three-dimensional real-time observation result into a bird's-eye view.
8 . The information processing apparatus according to claim 5 ,
wherein the prior map corresponds to a map obtained by processing of reducing resolution of the three-dimensional real-time observation result to an extent enabling the communication.
9 . An information processing method comprising:
generating a three-dimensional real-time observation result based on self-position estimation information and three-dimensional distance measurement information obtained from a sensor;
acquiring a prior map corresponding to the three-dimensional real-time observation result;
aligning the three-dimensional real-time observation result with the prior map; and
expanding the three-dimensional real-time observation result based on the prior map; and
determining a flight route based on the three-dimensional real-time observation result having been expanded, and
wherein the prior map includes information related to recognized environmental structure including at least one of a topography, a wall, or a building,
wherein the expanding of the three-dimensional real-time observation result corresponds to semantic segmentation of the recognized environmental structure so that an expanded area of the three-dimensional real-time result is continuous for same semantics within and outside a detection range of the sensor, and
wherein the method further comprises:
performing the semantic segmentation on the three-dimensional real-time observation result to determine whether continuity is present in semantics at a connection portion with respect to previously performed semantic segmentation of the prior map in relation to the recognized environmental structure; and
expanding, with a result of the semantic segmentation, a plane at the connection portion.
10 . A flight object comprising:
circuitry configured to
generate a three-dimensional real-time observation result based on self-position estimation information and three-dimensional distance measurement information obtained from a sensor,
acquire a prior map corresponding to the three-dimensional real-time observation result,
align the three-dimensional real-time observation result with the prior map,
expand the three-dimensional real-time observation result based on the prior map, and
determine a flight route based on the three-dimensional real-time observation result having been expanded,
wherein the prior map includes information related to recognized environmental structure including at least one of a topography, a wall, or a building,
wherein the expanding of the three-dimensional real-time observation result corresponds to semantic segmentation of the recognized environmental structure so that an expanded area of the three-dimensional real-time result is continuous for same semantics within and outside a detection range of the sensor, and
wherein the circuitry is further configured to
perform the semantic segmentation on the three-dimensional real-time observation result to determine whether continuity is present in semantics at a connection portion with respect to previously performed semantic segmentation of the prior map in relation to the recognized environmental structure, and
expand, with a result of the semantic segmentation, a plane at the connection portion.
11 . The flight object according to claim 10 ,
wherein the circuitry is configured to acquire the prior map from a different flight object from the flight object through communication.
12 . The flight object according to claim 11 ,
wherein the prior map corresponds to a map based on the three-dimensional real-time observation result generated by the different flight object.
13 . The flight object according to claim 10 ,
wherein the prior map corresponds to a map obtained by processing of cutting the three-dimensional real-time observation result at a certain height and converting the cut three-dimensional real-time observation result into a bird's-eye view.
14 . The flight object according to claim 10 ,
wherein the prior map corresponds to a map obtained by processing of reducing resolution of the three-dimensional real-time observation result to an extent enabling the communication.
15 . The flight object according to claim 10 ,
wherein the circuitry is further configured to
perform plane detection on the three-dimensional real-time observation result, and
expand, with a result of the plane detection, the plane based on information regarding the prior map.