Augmented path planning for automotive applications
The present disclosure relates to a method for augmenting capabilities of an Automated Driving System (ADS) of a vehicle. The method includes locally processing, by means of a perception module of the ADS, sensor data obtained from one or more sensors of the vehicle in order to generate a local world-view of the ADS. The sensor data is associated with a time period and includes information about a surrounding environment of the vehicle during the time period. The method further includes generating a local candidate path to be executed by the ADS based on the generated local world-view of the ADS, and transmitting a first set of data to a remote system. The first set of data is associated with the time period and including information about the surrounding environment of the vehicle during the time period.
1 . A computer-implemented method for augmenting capabilities of an Automated Driving System (ADS) of a vehicle, the method comprising:
locally processing, using a perception module of the ADS, sensor data obtained from one or more sensors of the vehicle in order to generate a local world-view of the ADS, wherein the sensor data is associated with a time period and comprises information about a surrounding environment of the vehicle during the time period;
generating a local candidate path to be executed by the ADS based on the generated local world-view of the ADS;
transmitting a first set of data to a remote system, the first set of data being associated with the time period and comprising information about the surrounding environment of the vehicle;
receiving off-board processed data from the remote system, the off-board processed data being indicative of a supplementary candidate path to be executed by the ADS;
selecting a path, from the local candidate path and the supplementary candidate path based on at least one constraint, for execution by the ADS;
generating, at an output, a signal indicative of the selected path for execution;
generating a back-up path based on the local world-view of the ADS;
evaluating the selected path for execution against a set of predefined safety constraints; and
in response to the selected path for execution fulfilling the set of predefined safety constraint, transmitting a first control signal so to execute the selected path for execution; and
in response to the selected path for execution failing to fulfil the set of predefined safety constraints, transmitting a second control signal so to execute the generated back-up path, and
generating a second feedback signal to the remote system, wherein the second feedback signal is indicative of the comparison of the selected path for execution against the set of predefined safety constraints.
2 . The method according to claim 1 , wherein the transmitted first set of data comprises at least a subset of the sensor data obtained from one or more sensors of the vehicle.
3 . The method according to claim 2 , wherein the sensor data is raw sensor data.
4 . The method according to claim 1 , wherein the first set of data comprises the locally processed sensor data.
5 . The method according to claim 4 , wherein the first set of data comprises at least one of:
object-level data originating from at least one sensor of the vehicle;
fused object-level data from a plurality of data sources; or
the local world-view of the ADS.
6 . The method according to claim 1 , further comprising:
generating, at an output, a first feedback signal for transmission to the remote system, wherein the first feedback signal is indicative of the selected candidate path.
7 . The method according to claim 1 , wherein the transmitting of the first set of data comprises streaming, in real-time, the first set of data to the remote system.
8 . The method according to claim 1 , wherein the first set of data is time-stamped.
9 . The method according to claim 8 , further comprising:
evaluating the received off-board processed data against a latency threshold; and
wherein the selection of the path from the local candidate path and the supplementary candidate path is only performed if the received off-board processed data doesn't exceed the latency threshold.
10 . The method according to claim 9 , wherein evaluating the received off-board processed data against a latency threshold comprises:
evaluating time-stamps of the first set of data against the latency threshold in order to determine a validity of the supplementary candidate path.
11 . The method according to claim 9 , further comprising:
discarding the received off-board processed data if the received off-board processed data exceeds the latency threshold.
12 . The method according to claim 1 , wherein the off-board processed data is further indicative of a supplementary world-view of the ADS, the method further comprising:
forming an augmented world-view of the ADS based on the generated local world-view and the supplementary world-view; and
generating, at an output, a signal indicative of the augmented world-view of the ADS.
13 . A non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of a vehicle control system, the one or more programs comprising instructions for performing the method according to claim 1 .
14 . An in-vehicle system for augmenting capabilities of an Automated Driving System (ADS) of a vehicle, the in-vehicle system comprising one or more processors and memory storing one or more programs configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the method according to claim 1 .
15 . A ground vehicle comprising:
at least one sensor configured to monitor a surrounding environment of the vehicle;
at least one communication device for transmitting/receiving wireless signals to/from a remote system via a communication network; and
an in-vehicle system according to claim 14 .