Action potential based detectors
Disclosed herein are systems and methods for action potential-based object detection. Received signals corresponding to multiple chirps can be grouped based on temporal or spatial attributes. Within these groups, successful detections can be identified when at least one signal satisfies an action potential threshold. The presence of a valid object is confirmed when the number of groups with successful detections satisfies a predetermined detection threshold.
1 . A radar system for object detection in an environment, comprising:
a radar transmitter, configured to emit a plurality of chirps to the environment;
a radar receiver, configured to collect a plurality of signals reflected from objects within the environment to generate a single observed frame of the environment, the plurality of signals being responsive to the plurality of chirps;
a processor; and
a memory device including instructions that, when executed by the processor, enable the radar system to:
group the plurality of signals within the single observed frame into a plurality of groups based on both respective temporal attributes and spatial attributes;
determine whether at least one group includes a successful detection, thesuccessful detection comprising at least one signal in the at least one group exceeding an action potential threshold, wherein the action potential threshold is associated with a minimum signal strength or signal-to-noise ratio required to classify the at least one signal as a potential target within the at least one group;
determine whether a number of groups having a successful detection exceeds a detection threshold; and
establish an object detection within the single observed frame when the number of groups having a successful detection exceeds the detection threshold.
2 . The radar system of claim 1 , wherein the instructions, when executed, further enable the radar system to:
adapt the plurality of groups and the detection threshold based on feedback from system sensors showing presence of jammer, interference, or reflection from an object which has a sudden change in position.
3 . The radar system of claim 1 , wherein the instructions, when executed, further enable the radar system to:
determine the plurality of signals are derived from pulses transmitted at different time intervals; and
group the plurality of signals based on respective temporal attributes.
4 . The radar system of claim 1 , wherein the instructions, when executed, further enable the radar system to:
determine the plurality of signals originate from different spatial zones; and
group the plurality of signals based on respective spatial attributes.
5 . The radar system of claim 1 , wherein the spatial attributes comprise at least a distribution of radars on a platform from which the plurality of signals are received.
6 . The radar system of claim 1 , wherein the temporal attributes comprise time domain characteristics of the plurality of signals, wherein the time domain characteristics include at least one of per chirp data or per subframe data.
7 . The radar system of claim 1 , wherein the instructions, when executed, further enable the radar system to:
integrate the plurality of chirps based on one of a subframe or frame.
8 . The radar system of claim 1 , wherein the instructions, when executed, further enable the radar system to:
integrate the plurality of groups based on one of coherent integration or non-coherent integration.
9 . The radar system of claim 8 , wherein the instructions, when executed to integrate the at least one signal within the plurality of groups based on coherent integration, further enable the radar system to:
average the at least one signal; and
calculate power of the at least one signal based on a phase of the at least one signal.
10 . The radar system of claim 8 , wherein the instructions, when executed to integrate the at least one signal within the plurality of groups based on non-coherent integration, further enable the radar system to:
calculate power of the at least one signal without taking into account a phase of the at least one signal; and
average the at least one signal.
11 . The radar system of claim 8 , wherein the instructions, when executed, further enable the radar system to:
determine a type of integration to be used for the plurality of groups based on at least one of environmental conditions, target characteristics, or interference and jamming conditions, wherein the environmental conditions comprise multipath effects, the target characteristics include target reflectivity, and the interference and jamming conditions include presence of other signal sources or reflectors in the environment.
12 . The radar system of claim 1 , wherein the instructions, when executed, further enable the radar system to:
calculate a probability of detection and a probability of false alarm based on a number of successful detections out of total groups within the single observation frame.
13 . A computer-implemented method, comprising:
obtaining a plurality of signals reflected from objects within an environment to generate a single observed frame, the plurality of signals being responsive to a plurality of chirps;
grouping the plurality of signals within the single observed frame into a plurality of groups based on respective temporal and spatial attributes, the temporal attributes comprising time domain characteristics of the plurality of signals per subframe data;
determining at least one group includes a successful detection, the successful detection comprising at least one signal exceeding an action potential threshold, wherein the action potential threshold is associated with a minimum signal strength or signal-to-noise ratio required to classify the at least one signal as a potential target within the at least one group;
determining a number of groups having a successful detection exceeds a detection threshold; and
establishing an object detection within the single observed frame when the number of groups having a successful detection exceeds the detection threshold;
adapting the plurality of groups based on feedback from system sensors showing presence of jammer or interference.
14 . The computer-implemented method of claim 13 , further comprising:
determining whether the plurality of signals are derived from pulses transmitted at different time intervals or originate from different spatial zones; and
grouping the plurality of signals based on a respective attribute of derivation, wherein temporal signals are grouped based on temporal attributes, and spatial signals are grouped based on spatial attributes.
15 . The computer-implemented method of claim 13 , further comprising:
integrating the plurality of groups based on one of coherent integration or non- coherent integration.
16 . The computer-implemented method of claim 15 , further comprising:
determine a type of integration to be used for the plurality of groups based on at least one of environmental conditions, target characteristics, or interference and jamming conditions, wherein the environmental conditions comprise multipath effects, the target characteristics include target reflectivity, and the interference and jamming conditions include presence of other signal sources or reflectors in the environment.
17 . A non-transitory computer readable storage medium storing instructions that, when executed by at least one processor of a computing system, causes the computing system to:
obtain a plurality of signals reflected from objects within an environment to generate a single observed frame, the plurality of signals being responsive to a plurality of chirps;
group the plurality of signals within the single observed frame into a plurality of groups based on respective temporal or spatial attributes, the temporal attributes comprising time domain characteristics of the plurality of signals per subframe data;
determine at least one group includes a successful detection, the successful detection comprising at least one signal exceeding an action potential threshold, wherein the action potential threshold is associated with a minimum signal strength or signal-to-noise ratio required to classify the at least one signal as a potential target within the at least one group;
determine a number of groups having a successful detection exceeds a detection threshold;
establish an object detection within the single observed frame when the number of groups having a successful detection exceeds the detection threshold; and
adapting the plurality of groups based on feedback from system sensors in subsequent object detections.