Buttcloud

A private research vault for my PhD research on fallback path planning under camera degradation.

PhD thesis End-to-end AI for Automated Driving: Fallback Path Planner under Camera Degradation with Runtime Safety Supervision for Auditable Fallback Decisions

PhD candidate Ing. Lemnariu Flaviu Rares Technical University of Cluj-Napoca

PhD coordinator Prof. Dr. Ing. MUNTEAN Ionut Technical University of Cluj-Napoca

Collaborator Assoc. Prof. dr. ing. MORRIS Brendan University of Nevada

View repository Become a contributor

Research roadmap From infrastructure to auditable fallback decisions

01Connect more computeAdditional PC GPU workers.
02Build the simulatorPhysics engine and controlled scenarios.
03Paper on the projectDocument the platform and research direction.
04Run Alpamayo on videoImprove the video generation pipeline.
05Compare architecturesBenchmark candidate model families.
06Define safe fallbackTrigger, audit trail, and measures.
07Run the studyAnalyse normal and degraded scenarios.

Workspace & platform

myphd is the private workspace for this PhD: it organises visual driving evidence, runs selected models on remote GPUs, and keeps the data, configuration, and result of each experiment together for later review.

Pre-push checks

→

GitHub repository

→

GitHub Actions

→

Render deployment

myphd platform Deployed research workspace

Web console Research workspace

→

API gateway Authentication & routing

Storage service Evidence & integrity

↓

Cloudflare R2
visual files

Metadata service Users, records & audit

↓

Aiven PostgreSQL
metadata

Compute service Inference & lifecycle

↓

RunPod GPU worker
Alpamayo 1.5

Health checks · retry · logging · compute orchestration

Research question

Can neural networks extract sufficient task-relevant features from severely corrupted camera input, then support a safe fallback decision instead of simply handing control away?

Gap

Current approaches often depend on LiDAR, perfect real-time HD maps, redundancy, or conservative clock-out behavior; usable feature extraction from degraded camera images remains missing.

Methodology

Use Alpamayo as the nominal driving baseline and fallback trigger, Cosmos for synthetic edge cases, plus Bosch and open datasets for grounding and validation.

Build 2b93479 · Sep 28, 2026 02:26 EEST

Select a sequence

Directory Log

Buttcloud

Select a sequence

Directory Log

Raw SQL Executor

Identity Management

Compute Analytics

Start GPU Instance