M3: Motion Distortion Correction and Timing Robustness Evaluation

Aberta
#747 0 comentários 0 reações 0 responsáveis Ver no GitHub

Mantenedores costumam responder em até 2 dias

Ninguém assumiu esta issue ainda.

Avaliação

Dificuldade
5/5
Tempo estimado
Mais de uma semana
Facilidade para iniciantes
20/100
Tipo de issue
Funcionalidade
Clareza
Razoavelmente clara
Status de atividade
Ativa
Stack de tecnologia
rust

Direção de pesquisa

Start in the Awkernel localization pipeline and locate the LiDAR preprocessing stages where per-point timestamps are still available before downsampling, then trace how NDT and EKF consume those points. The issue names no files or tests, so first map the existing preprocessing, timing, and input-handling paths and identify any reproducible evaluation harness. Done means motion distortion correction is integrated before timing data is discarded, and delayed, missing, and overloaded input scenarios have documented policies and reproducible accuracy/latency results.

Escrita pelo modelo de indexação a partir do texto da issue.

Descrição

Integrate LiDAR motion distortion correction into the Awkernel localization pipeline and evaluate its accuracy and timing behavior under delayed, missing, and overloaded input conditions.

Scope:

  • Motion distortion correction using per-point timestamps and vehicle motion estimates
  • Integration before downsampling stages that discard required per-point timing information
  • Validation of timestamp alignment, coordinate transforms, and motion-data availability
  • Controlled injection of input delays, timestamp offsets, dropped messages, and computational overload
  • Explicit policies for stale or missing inputs, buffer limits, and processing overruns
  • Measurement of localization accuracy, end-to-end latency, input data age, deadline misses, and dropped-data rates

Completion criteria:

  • Motion distortion correction operates within the integrated preprocessing, NDT, and EKF pipeline.
  • Corrected point clouds and localization outputs satisfy predefined tolerances against reference results under nominal conditions.
  • Timing and abnormal-input scenarios are reproducible, with documented expected behavior and acceptance criteria.
  • Stale inputs, missing data, and processing overruns are detected and handled according to the defined policies.
  • Accuracy and timing trade-offs are reported with datasets, configurations, and reproduction steps.

Out of scope:

Live sensor fault recovery, vehicle-level safety certification, closed-loop vehicle control, and formal worst-case execution-time guarantees.

Linguagem predominante
Rust
Estrelas
282
Forks
12
Merge médio
2d 9h
PRs com merge (30d)
28

Preparar o ambiente

Este projeto não oferece contêiner de desenvolvimento, Dockerfile nem guia de contribuição, então a configuração fica por sua conta: comece pelo README e veja nosso guia da primeira contribuição para os passos gerais.

Primeiros passos

  1. Leia a issue inteira e depois o guia de contribuição do projeto.
  2. Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
  3. Faça um fork do repositório e trabalhe em uma branch.
  4. Abra um pull request que referencie o número da issue.

Mais de tier4/awkernel

Todas as issues de tier4/awkernel

Issues semelhantes

Mais issues de Rust

Receba novas issues na sua caixa de entrada

Um resumo curto de issues do GitHub para quem está começando.