SidewalkPilot-v3.1b maps one 320x180 OpenCV BGR frame to steering control for the SidewalkPilot RC car. Best-validation checkpoint from the v3.1 hybrid-head run.

Model Details

Developer: Ram Shreyas Naik Sabavat
Series: 3.x
Architecture: SidewalkPilotV3 CNN, approximately 5.53 million parameters
Model type: 9-class steering classification plus within-bucket offsets and throttle
Checkpoint role: best-validation
Artifact: SidewalkPilot-v3.1b.onnx (FP32 ONNX)
Checkpoint created: 2026-07-03 18:48 PDT
Input: [batch, 3, 180, 320], OpenCV BGR
Preprocessing: resize to 320x180, then (x / 255 - 0.5) / 0.5
Output: [batch, 19]: 9 class logits, 9 offsets, and throttle

Output Decoding

text

class_id = argmax(output[0:9])
fraction = sigmoid(output[9 + class_id])
steering_deg = bucket_low[class_id] + fraction * bucket_width[class_id]
throttle = sigmoid(output[18])  # not used by the current runtime

Logical steering uses 0 for full left, 90 for straight, and 180 for full right. The throttle output is not deployed because the collected throttle labels do not contain enough variation to train useful throttle control.

Evaluation Setup

Evaluation set: 81,237 current Series 3 real field images
Purpose: training-set fit check, not held-out generalization proof
Error unit: logical steering degrees
Selection priority: balanced 9-bucket accuracy and turn recall first; MAE is supporting evidence
Cross-series warning: do not compare these numbers directly with Series 1/2, which use their original 2,224-image dataset

Chronological Metrics Through This Version

Model	Bal9	Turn exact	Turn +/-1	Straight exact	MAE	Median AE	Signed error
`3.0`	`16.0%`	`15.3%`	`42.9%`	`23.4%`	`18.971`	`13.623`	`-3.594`
`3.0b`	`15.9%`	`14.8%`	`42.3%`	`24.6%`	`18.450`	`13.129`	`-3.944`
`3.1`	`28.1%`	`26.8%`	`53.3%`	`55.2%`	`22.647`	`9.729`	`-2.353`
`3.1b` (this model)	`27.4%`	`25.8%`	`52.3%`	`56.7%`	`20.958`	`9.591`	`-3.769`

Class-Balanced Ranking Through This Version

Rank	Model	Bal9	Turn exact	Turn +/-1	MAE	Median AE	Signed error
`1`	`3.1`	`28.1%`	`26.8%`	`53.3%`	`22.647`	`9.729`	`-2.353`
`2`	`3.1b`	`27.4%`	`25.8%`	`52.3%`	`20.958`	`9.591`	`-3.769`
`3`	`3.0`	`16.0%`	`15.3%`	`42.9%`	`18.971`	`13.623`	`-3.594`
`4`	`3.0b`	`15.9%`	`14.8%`	`42.3%`	`18.450`	`13.129`	`-3.944`

Current Version Snapshot

Balanced 9-bucket exact: 27.4%
Turn exact: 25.8%
Turn within one bucket: 52.3%
Straight exact: 56.7%
MAE: 20.958 degrees
Median absolute error: 9.591 degrees
Signed error: -3.769 degrees

Intended Use

Small RC-car autonomy experiments
Sidewalk/path steering research
Jetson ONNX/TensorRT deployment experiments

Limitations and Safety

This model does not identify obstacles, prove a clear path, estimate confidence, or detect out-of-distribution scenes. Shadows, lighting changes, curb geometry, driveways, camera movement, and underrepresented turns can cause unsafe steering. Keep independent LiDAR emergency braking, manual takeover, conservative speed limits, and bounded operating conditions above model output. v3.3 through v3.4b have not yet received a physical-car field verdict.

Reproducibility

artifact_manifest.json records the artifact SHA-256, tensor signature, checkpoint role, evaluation set, and current report metrics.

ram-shreyas-naik-sabavat/SidewalkPilot-v3.1b

SidewalkPilot-v3.1b