SidewalkPilot-v3.4

SidewalkPilot-v3.4 maps one 320x180 OpenCV BGR frame to steering control for the SidewalkPilot RC car. It is the final-epoch checkpoint from softened tree-shadow and left/right-balanced training and is the current field-selected SidewalkPilot model.

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: final-epoch
  • Field status: selected after July 13, 2026 physical-car comparison
  • Artifact: SidewalkPilot-v3.4.onnx (FP32 ONNX)
  • Checkpoint created: 2026-07-12 21:18 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

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 27.4% 25.8% 52.3% 56.7% 20.958 9.591 -3.769
3.2 34.0% 31.1% 57.7% 52.4% 16.776 9.648 -1.474
3.2b 25.1% 19.8% 46.0% 67.2% 14.457 5.909 -4.691
3.3 27.1% 21.2% 48.1% 68.5% 14.630 5.204 -5.351
3.3b 19.2% 10.6% 36.5% 78.0% 16.460 2.183 -8.287
3.4 (this model) 33.3% 32.6% 60.7% 65.5% 14.377 4.859 +0.799

Class-Balanced Ranking Through This Version

Rank Model Bal9 Turn exact Turn +/-1 MAE Median AE Signed error
1 3.2 34.0% 31.1% 57.7% 16.776 9.648 -1.474
2 3.4 33.3% 32.6% 60.7% 14.377 4.859 +0.799
3 3.1 28.1% 26.8% 53.3% 22.647 9.729 -2.353
4 3.1b 27.4% 25.8% 52.3% 20.958 9.591 -3.769
5 3.3 27.1% 21.2% 48.1% 14.630 5.204 -5.351
6 3.2b 25.1% 19.8% 46.0% 14.457 5.909 -4.691
7 3.3b 19.2% 10.6% 36.5% 16.460 2.183 -8.287
8 3.0 16.0% 15.3% 42.9% 18.971 13.623 -3.594
9 3.0b 15.9% 14.8% 42.3% 18.450 13.129 -3.944

Current Version Snapshot

  • Balanced 9-bucket exact: 33.3%
  • Turn exact: 32.6%
  • Turn within one bucket: 60.7%
  • Straight exact: 65.5%
  • MAE: 14.377 degrees
  • Median absolute error: 4.859 degrees
  • Signed error: +0.799 degrees

Field Evaluation

v3.4 was tested on the physical car on July 13, 2026 against v3.4b, v3.3, and v3.3b. The comparison included harsh-shadow cases and normal left/right turns. The operator reported that v3.4 completed every shadow case presented and ranked first of the four models, so it became the current field-selected checkpoint.

This result also shows why selection is not based on MAE alone. v3.4b has a slightly lower MAE, while v3.4 has stronger balanced-nine-class and turn recall and performed better on the car.

The field result is qualitative. The exact route, weather, duration, manual-takeover count, and linked clip identifiers were not preserved. The claim is limited to the cases presented during that comparison.

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. Field selection on July 13 does not establish general sidewalk, weather, or pedestrian safety.

Reproducibility

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

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading