Lesson 1GPS/IMU and time synchronization: RTK, PPP options, IMU drift characteristics, timestamping and synchronization protocolsThis section introduces GPS, IMU, and timing requirements. It compares RTK and PPP, describes IMU drift characteristics, and explains timestamping and synchronization protocols needed for precise, low-latency sensor fusion and localization.
GNSS accuracy and availability limitsRTK and PPP correction strategiesIMU bias, noise, and drift modelsTime bases and timestamp policiesPPS, PTP, and IEEE 1588 usageClock monitoring and fault handlingLesson 2Perception stack components: detection, classification, tracking, lane model estimation, gap acceptance estimationThis section decomposes the perception stack into detection, classification, tracking, and lane modeling. It also covers gap acceptance estimation and how these components interact to support safe lane keeping and maneuver decisions.
Object detection and region proposalsObject classification and attributesMulti-object tracking and ID managementLane model estimation and qualityGap acceptance and TTC estimationInterfaces to planning and controlLesson 3Sensor roles by function: segmentation of responsibilities for lane keeping, object detection/tracking, and localizationThis section assigns functional roles to each sensor type. Learners see how radar, lidar, cameras, and GNSS/IMU share responsibilities for lane keeping, object detection and tracking, and localization in a balanced, fault-tolerant design.
Lane keeping sensing responsibilitiesObject detection and confirmation rolesLongitudinal and lateral tracking dutiesLocalization and map alignment rolesRedundancy and graceful degradationRole allocation for highway pilotLesson 4Calibration, extrinsics, and online self-checks: calibration verification, boresight checks, and integrity monitoringThis section focuses on calibration and integrity monitoring. It covers extrinsic and intrinsic calibration, boresight checks, online self-checks, and health metrics that detect misalignment or sensor faults before they degrade safety.
Intrinsic calibration of cameras and lidarExtrinsic calibration between sensorsBoresight checks for radar and camerasOnline self-checks and residual testsHealth metrics and fault thresholdsRecalibration triggers and workflowsLesson 5Typical automotive sensor specs: front radar (ranges, resolution, update rate, field of view)This section reviews front radar specifications and their impact on design. It covers range, range and velocity resolution, update rate, field of view, and how these parameters affect highway cut-in detection, tracking stability, and safety margins.
Maximum and minimum detection rangeRange, angle, and velocity resolutionUpdate rate and tracking latencyHorizontal and vertical field of viewMulti-path, clutter, and interferenceHighway pilot radar performance needsLesson 6Typical automotive camera specs: resolution, frame rate, dynamic range, lens FOV, mounting and calibration needsThis section covers camera specifications relevant to autonomous driving. It addresses resolution, frame rate, dynamic range, lens field of view, and mounting and calibration needs, linking each to lane detection, object recognition, and fusion.
Image resolution and pixel sizeFrame rate and exposure controlDynamic range and HDR techniquesLens FOV and distortion profilesMounting rigidity and placementIntrinsic and extrinsic calibrationLesson 7Typical automotive lidar specs: range, angular resolution, point rate, weather performance, mounting considerationsThis section explains automotive lidar specifications and tradeoffs. Learners examine range, angular resolution, point rate, weather and contamination performance, and mounting constraints that influence coverage, occlusions, and fusion design.
Detection range and reflectivity limitsHorizontal and vertical angular resolutionPoint rate, scan pattern, and densityRain, fog, and dust performanceVibration, height, and occlusion issuesCleaning, heating, and contaminationLesson 8Sensor fusion architectures: low-, mid-, high-level fusion tradeoffs and recommended approach for highway pilotThis section surveys sensor fusion architectures and tradeoffs. It contrasts low-, mid-, and high-level fusion, then motivates a recommended mid-level approach for highway pilot, focusing on robustness, latency, and implementation complexity.
Low-level fusion and raw data sharingMid-level fusion with object listsHigh-level fusion of decisionsLatency, bandwidth, and compute costsFailure isolation and redundancyHighway pilot fusion reference designLesson 9HD map data attributes: lane-level geometry, speed limits, merge tags, lane connectivity, confidence and versioningThis section details HD map lane geometry, attributes, and metadata. Learners see how speed limits, lane connectivity, merge tags, confidence, and versioning support planning, localization, and safe behavior in changing road networks.
Lane centerlines and boundariesLane-level speed limits and rulesMerge, split, and turn lane taggingLane connectivity graphs and topologyConfidence scores and freshness flagsMap versioning and change management
