Recursively apply patterns for pathfinding
Details
- External ID
- 47143717
- Source
- HN
- Company
- —
- Product
- Recursively apply patterns for pathfinding
- Website domain
- vercel.app
- Launched
- Feb. 24, 2026
- Cohort
- —
- Upvotes
- 26
- Upvotes percentile
- 0.7284366576819407
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
I've been begrudgingly working on autorouters for 2 years, looking for new techniques or modern methods that might allow AI to create circuit boards.One of the biggest problems in my view for training an AI to do autorouting is the traditional grid-based representation of autorouting problems which challenges spatial understanding. But we know that vision models are very good at classifying, so I wondered if we could train a model to output a path as a classification. But then how do you represent the path? This lead me down the track of trying to build an autorouter that represented paths as a bunch of patterns.More details: https://blog.autorouting.com/p/the-recursive-pattern-pathfin...
Enrichment
- Theme
- 3d modeling and graphics engines
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- Not AI
- Project type
- Hobby / open-source project
- Normalized one-liner
- pathfinding algorithm library
- Manually corrected
- False
Could you build this?
No Designing novel pathfinding algorithms and recursive pattern-based autorouting for printed circuit board (PCB) design is a complex domain in computational geometry and electronic design automation (EDA). This requires deep specialized algorithmic research that AI coding assistants cannot independently invent or solve.
What it would actually take: Building an AI-driven PCB autorouter requires deep knowledge of EDA physical design, computational geometry, and multi-layer routing heuristics (e.g., A*, negotiated-congestion routing, or reinforcement learning). The core pipeline requires a custom geometric engine, DRC (design rule check) validation, and spatial graph representations rather than naive 2D grids. Achieving production viability demands a team with PhD-level expertise in CAD/EDA algorithms and hardware engineering.
Discussion
5 comments analyzed.
Competitors mentioned: Polyanya/any-angle pathfinding, OpenROAD (chip design autorouting), Game developer pathfinding techniques
Concerns raised: Inefficiencies in AI autorouting results, Baked navmesh approach not equivalent to A* pathfinding, VLSI algorithms oriented toward repeated patterns, not typical PCBs
Feature requests: More academic papers/critical analysis of autorouting approaches, Design rule checking integration
Competitors
Other products that read as similar to this one — 83 launches clear the similarity bar, closest 8 shown.
Attention rank: #25 of 84 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 118 days after the earliest competitor.
- GPU-Based Autorouting for KiCad · hn · 2025-10-29 · 8 upvotes · similarity 0.44
- vector · github · 2026-09-19 · 16 upvotes · similarity 0.41
- Map Animation · ph · 2026-09-21 · 1 upvotes · similarity 0.40
- Pathwise · ph · 2026-09-11 · 1 upvotes · similarity 0.39
- TripPathAI · ph · 2026-09-23 · 3 upvotes · similarity 0.38
- Neural Net Flies Navigate through a maze · hn · 2025-12-28 · 14 upvotes · similarity 0.38
- Autostep - Uncover Repetitive Tasks Ready For AI · yc · 2026-02-27 · 33 upvotes · similarity 0.37
- Algotrek · hn · 2026-07-16 · 13 upvotes · similarity 0.37
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.