Hey, I've been tweaking a pathfinding algorithm that might outpace even your city shortcuts—care to test it out on the streets?

import heapq # Simple A* pathfinder for a 2D grid where 0=free, 1=obstacle (streetcar, pigeon, etc.) def astar(grid, start, goal): rows, cols = len(grid), len(grid[0]) def heuristic(a, b): return abs(a[0]-b[0]) + abs(a[1]-b[1]) # Manhattan distance open_set = [] heapq.heappush(open_set, (0 + heuristic(start, goal), 0, start)) came_from = {} g_score = {start: 0} while open_set: _, current_g, current = heapq.heappop(open_set) if current == goal: path = [] while current in came_from: path.append(current) current = came_from[current] path.append(start) return path[::-1] for dx, dy in [(1,0),(-1,0),(0,1),(0,-1)]: nx, ny = current[0]+dx, current[1]+dy neighbor = (nx, ny) if 0 <= nx < rows and 0 <= ny < cols and grid[nx][ny] == 0: tentative_g = current_g + 1 if neighbor not in g_score or tentative_g < g_score[neighbor]: g_score[neighbor] = tentative_g f = tentative_g + heuristic(neighbor, goal) heapq.heappush(open_set, (f, tentative_g, neighbor)) came_from[neighbor] = current return None # no path found # Example usage grid = [ [0,0,0,0,0], [0,1,1,1,0], [0,0,0,1,0], [1,1,0,0,0], [0,0,0,1,0] ] start = (0,0) goal = (4,4) path = astar(grid, start, goal) print(path)

Got it, adding a corner turn check. Will reroute if the next step would put us directly into a blocked cell. Here’s the tweak to the neighbor loop. It should catch tight corners before you step on them. Let's run it.

Looks solid—keeps you away from the obstacles and uses the shortest route I see. If you hit a snag on a real map, just feed in the updated grid and it’ll re‑calculate. Good luck out there, and if the pigeon shows up, this should still hold up.

Good luck out there, and if the pigeons decide to take a detour, just tweak the grid again. Stay safe.

Sounds good—just keep checking the grid for any new obstacles and you’ll stay on the path. Happy hacking.