.png){kind=icon}
.png){kind=icon}
Return
All-Optically Triggered In-Sensor Collision Detection and Warning Based on 2D Complementary Material Devices
.png){kind=icon}
PRE
AI
DOI：10.1002/adfm.202402677.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Precise and timely collision detection and warning are essential to ensure the safety of autonomous driving. However, existing collision detection systems based on image sensors and radars are prone to misjudgment in adverse environments such as darkness or rain. The lobula giant movement detector (LGMD) neuron found in locusts achieves potential collision detection in unpredictable environments without the need for object recognition algorithms. Existing artificial collision detectors inspired by LGMD suffer from complex device structures and sophisticated operating modes. Here, an LGMD-inspired all-optically triggered in-sensor collision detector is presented by 2D complementary material devices (2D-CMDs) composed of n-type molybdenum disulfide (MoS2) and p-type platinum diselenide (PtSe2) connected in series. The proposed 2D-CMDs couple the positive photoconductivity of MoS2 and negative photoconductivity of PtSe2 in response to looming light, successfully mimicking the antagonism of excitatory and inhibitory responses in LGMD neurons to generate a nonmonotonic escape response. The 2D-CMDs exhibit a simple device structure and all-optically controlled operation mode, consuming only 1 nJ of energy for each collision detection. Furthermore, in-sensor real-time collision warning is realized by employing a Recurrent Neural Network (RNN) to predict alarm time based on the escape response of the proposed 2D-CMDs. Precise and timely collision detection and warning are essential to ensure the safety of autonomous driving. Existing artificial collision detectors inspired by lobula giant movement detector (LGMD) neuron suffer from complex device structures and sophisticated operating modes. Here, a LGMD-inspired all-optically triggered in-sensor collision detector is presented by 2D complementary material devices (2D-CMDs) composed of n-type MoS2 and p-type PtSe2 connected in series. The 2D-CMDs exhibit a simple structure and all-optically triggered collision detection mechanism, consuming only 1 nJ of energy for each collision detection. image
Keywords:
2D material
collision detection and warning
in-sensor computing
LGMD
neuromophic computing
Journal
IF:
19
Papers:
3.4W
Citations:
32.1W