Abstract: Systems and techniques are provided for simulating LiDAR sensors. An example method includes generating, within a simulation environment, a first Light Detection and Ranging (LiDAR) measurement that corresponds to a first virtual beam transmission from a first channel of a first LiDAR sensor; generating, within the simulation environment, a second LiDAR measurement that corresponds to a second virtual beam transmission from a second channel of the first LiDAR sensor, wherein the first virtual beam transmission and the second virtual beam transmission are directed to a virtual object in the simulation environment; determining a channel measurement variance between the first channel and the second channel; and adjusting at least one of the first LiDAR measurement and the second LiDAR measurement based on the channel measurement variance.

Abstract: Systems and techniques of the present disclosure may access data from a time-of-flight (TOF) sensor of an autonomous vehicle (AV). The TOF sensor may have light signals and received reflections of those transmitted signals such that a set of simulation data can be generated. This set of simulation data may identify a distance to associate with an object that is different from a calibration distance. Equations may be used to identify a light signal amplitude, a signal to noise ratio (SNR), and a range inaccuracy due to noise from the accessed data. The identified the light signal amplitude, the SNR, and the range inaccuracy due to noise may have been identified using equations. Once the set of simulation data is generated, it may be saved for later access by a processor executing a simulation program used to train devices used to control the driving of an AV.

Abstract: Systems and techniques are provided for simulating LiDAR sensors. An example method includes generating, within a simulation environment, at least one virtual beam transmission from a LiDAR sensor using a beam divergence model, wherein the at least one virtual beam transmission includes a plurality of rays; determining one or more intensity parameters associated with one or more virtual beam receptions by the LiDAR sensor, wherein the one or more virtual beam receptions correspond to one or more rays from the plurality of rays that are reflected from one or more virtual objects; adjusting the one or more intensity parameters based on one or more transmission intensity weights corresponding to the one or more rays to yield one or more modified intensity parameters; and determining at least one object intensity parameter for each of the one or more virtual objects based on the one or more modified intensity parameters.

Abstract: Systems and techniques are provided for simulating a Light Detection and Ranging (LiDAR) transmission through at least partially transparent material. An example method can include receiving, within a simulation environment for an autonomous vehicle (AV), an angle of incidence that is formed between a simulated transmission from a simulated LiDAR sensor associated with the AV and a simulated at least partially transparent surface; determining, based on the angle of incidence, a probability of detecting at least one LiDAR return corresponding to a reflection of the simulated transmission from the simulated at least partially transparent surface; and generating simulated LiDAR perception data corresponding to the reflection of the simulated transmission from the simulated at least partially transparent surface based on a comparison between the probability and a target number, wherein the simulated LiDAR perception data includes a number of LiDAR returns.

Abstract: Systems and techniques are described for Light Detection and Ranging (LiDAR) noise modeling using machine learning (ML). An example method can include collecting, using one or more sensors, a first set of data for a simulation environment and generating, using the first set of data, a point cloud that represents and/or describes the simulation environment. The method can further include collecting, using the one or more sensors, a second set of data for a real-world environment and generating a noise model using the second set of data and a neural network. The method can also include generating, using the noise model and the point cloud, a noisy point cloud that represents and/or describes the real-world environment.

Abstract: Systems and techniques of the present disclosure may access data from a time-of-flight (TOF) sensor of an autonomous vehicle (AV). The TOF sensor may have light signals and received reflections of those transmitted signals such that a set of simulation data can be generated. This set of simulation data may identify a distance to associate with an object that is different from a calibration distance. Equations may be used to identify a light signal amplitude, a signal to noise ratio (SNR), and a range inaccuracy due to noise from the accessed data. The identified the light signal amplitude, the SNR, and the range inaccuracy due to noise may have been identified using equations. Once the set of simulation data is generated, it may be saved for later access by a processor executing a simulation program used to train devices used to control the driving of an AV.

Abstract: A combination of lookup tables for waveforms and several scaling and delay factors to accurately simulate touch and collision transducer sensor output without the complexity of solving the classical wave equation or performing convolutions in the frequency domain. TACT, as used herein, is a touch and collision transducer sensor used for detecting collisions. When the vehicle collides with an object a wave will be generated by the touch and collision transducer sensors. The waveform can take many forms depending on various parameter. Pre-recorded waveforms can be used to simulate the collisions and produce appropriate outputs. However, the present disclosure contemplates more complex, diverse waveforms which can be produced based on the existing pre-recorded libraries. To this end, simulated waveforms can be produced by scaling, filtering, delaying and combining with road noise, based on the impact material and contact area, at least in part.

Abstract: Techniques for simulating LIDAR data are described. In one embodiment, a method for simulating LIDAR data may include retrieving a simulated scene that simulates a real-world scene, the simulated scene including at least one target object having a reflectivity r and located at a range R from a LIDAR sensor, the LIDAR sensor having at least one intrinsic parameter; generating a probability of detection (Pd) drop-off function for the LIDAR sensor, wherein the Pd drop-off function is related to r, R, and the at least one intrinsic parameter; for each data point comprising a ray emitted by the LIDAR sensor that hits the target object, generating a Pd value using the Pd drop-off function; and determining based on the Pd value whether to drop the data point.