← Back
Home › Systems › AI applications

autonomous-driving

autonomous driving stack

Waymo

SystemTechniques · 23Primitives · 66 autonomous-driving Clock synchronizationdistributed · medium: Estimate a clock's offset from four timestamps, filter out queueing noise, and steer the clock smoothly; NTP gets about a millisecond, PTP with hardware timestamps under a microsecond.›Bev perceptionmachine-learning · medium: Lifting multi-camera features into a bird's-eye-view grid (lift-splat, BEV transformers) for detection and mappingImitation learningmachine-learning · medium: Learning policies from demonstrations: behavior cloning, DAgger, covariate shiftMulti-object trackingmachine-learning · medium: Turn per-frame detections (camera boxes or radar plots) into persistent IDs by predicting each track, gating, assigning and managing track births and deaths.›Object detectionmachine-learning · medium: A network turns an image into scored, classified boxes in one pass; anchor-based, anchor-free and set-prediction heads differ in how they assign labels and remove duplicates.›Point cloud processingmachine-learning · medium: Voxelization, pillars, k-NN and point networks for lidar perceptionTrajectory predictionmachine-learning · medium: Predicting multi-modal future paths of agents from history and map contextPID controllerrobotics · low: Drive a measured value to a setpoint with three terms on the error: proportional, integral, derivative. The default feedback loop for motors, heaters, drones and gimbals.›Kalman filterrobotics · low: Optimal recursive estimator for a linear system with Gaussian noise: fuses a motion model with noisy measurements into a state estimate plus its covariance.›Occupancy gridrobotics · low: Probabilistic grid map updated with log-odds from range sensorsCan bus framingembedded · low: CAN / CAN FD frames, bitwise arbitration, bit stuffing, CRC and error confinementReal time linux schedulingembedded · low: PREEMPT_RT, SCHED_FIFO/DEADLINE, CPU isolation and mlockall for low-jitter loopsKernel fusionml-training · low: Merge chains of memory-bound GPU ops into one kernel, so intermediates stay in registers instead of round-tripping through HBM.›Weight quantizationml-training · low: Store weights as 8/4-bit integers with per-group scales; decode is memory-bound, so 4-bit weights give about 3-4x tokens/s and fit 4x larger models.›Phase-locked loop (digital)signal-processing · low: Feedback loop that locks a local oscillator to the phase and frequency of an input tone; the core of carrier recovery, clock recovery and GNSS tracking.›Robust statisticsstatistics · low: Location and scale estimates (median, MAD, trimmed mean, Huber M-estimator) that stay correct when a minority of the data is garbage.›Homogeneous transformsgeometry · low: 4x4 affine and projective matrices, homogeneous coordinates, view and projection, normal matricesAttention variantsmachine-learning · low: Multi-head, multi-query, grouped-query, sliding-window and latent attention; same softmax(QKᵀ/√d)V core, different trade-offs between quality and KV-cache size.›Convolutional networksml-training · low: Layers that slide a small shared kernel over a grid, giving translation equivariance and few parameters; still the most compute-efficient choice for many vision tasks.›Transformer blockml-training · low: The decoder-only pre-norm block (attention plus MLP on a residual stream) behind every modern LLM, with exact shapes, parameter, FLOP and KV-cache counts.›Action chunkingmachine-learning · low: Policy predicts a chunk of future actions per step, executed with temporal ensembling for smooth controlData augmentationmachine-learning · low: Generate label-preserving variants of each training example on the fly to enlarge the effective dataset and bake in invariances.›Loss functionsmachine-learning · low: The scalar a model minimizes: cross-entropy for classes and tokens, MSE or Huber for values, each with a stable form and simple gradient.›+ 16 more techniques+ 50 more primitives

Similar systems

Share the most building blocks with this one.

autonomous-trucking 32 %vision-pipeline 19 %drone-delivery 17 %robot-vacuum 17 %

In-house systems

Named systems of this kind at large companies, with their paper or write-up.

Waymo DriverAlphabet