Upload folder using huggingface_hub

envs/warehouse_env/server/app.py

@@ -94,7 +94,7 @@ async def auto_step():
         )
 
 def _get_greedy_action() -> int:
-    """Simple greedy policy: move toward nearest target."""
+    """Simple greedy policy with obstacle avoidance."""
     robot_x, robot_y = warehouse_env.robot_position
 
     # Determine target location
@@ -121,21 +121,72 @@ def _get_greedy_action() -> int:
         if package:
             target_x, target_y = package.dropoff_location
         else:
-            return 4  # Try action
-
-    # Simple pathfinding: move closer on one axis at a time
-    if robot_x < target_x:
-        return 3  # RIGHT
-    elif robot_x > target_x:
-        return 2  # LEFT
-    elif robot_y < target_y:
-        return 1  # DOWN
-    elif robot_y > target_y:
-        return 0  # UP
-    else:
-        # At target location
+            return 5  # Try to drop off
+
+    # Check if at target location
+    if robot_x == target_x and robot_y == target_y:
         return 4 if warehouse_env.robot_carrying is None else 5
 
+    # Try to move toward target, checking for obstacles
+    # Priority: move on axis with larger distance first
+    dx = target_x - robot_x
+    dy = target_y - robot_y
+
+    # List of possible moves in order of preference
+    moves = []
+
+    if abs(dx) > abs(dy):
+        # Prioritize horizontal movement
+        if dx > 0:
+            moves.append((3, robot_x + 1, robot_y))  # RIGHT
+        elif dx < 0:
+            moves.append((2, robot_x - 1, robot_y))  # LEFT
+
+        if dy > 0:
+            moves.append((1, robot_x, robot_y + 1))  # DOWN
+        elif dy < 0:
+            moves.append((0, robot_x, robot_y - 1))  # UP
+    else:
+        # Prioritize vertical movement
+        if dy > 0:
+            moves.append((1, robot_x, robot_y + 1))  # DOWN
+        elif dy < 0:
+            moves.append((0, robot_x, robot_y - 1))  # UP
+
+        if dx > 0:
+            moves.append((3, robot_x + 1, robot_y))  # RIGHT
+        elif dx < 0:
+            moves.append((2, robot_x - 1, robot_y))  # LEFT
+
+    # Add perpendicular moves as fallback
+    if dx == 0 and dy != 0:
+        moves.append((3, robot_x + 1, robot_y))  # RIGHT
+        moves.append((2, robot_x - 1, robot_y))  # LEFT
+    elif dy == 0 and dx != 0:
+        moves.append((1, robot_x, robot_y + 1))  # DOWN
+        moves.append((0, robot_x, robot_y - 1))  # UP
+
+    # Try moves in order until we find a valid one
+    WALL = 1
+    SHELF = 2
+
+    for action_id, new_x, new_y in moves:
+        # Check bounds
+        if 0 <= new_x < warehouse_env.grid_width and 0 <= new_y < warehouse_env.grid_height:
+            # Check if cell is passable
+            if warehouse_env.grid[new_y][new_x] not in [WALL, SHELF]:
+                return action_id
+
+    # If no valid move toward target, try any valid move
+    for action_id, dx, dy in [(0, 0, -1), (1, 0, 1), (2, -1, 0), (3, 1, 0)]:
+        new_x, new_y = robot_x + dx, robot_y + dy
+        if 0 <= new_x < warehouse_env.grid_width and 0 <= new_y < warehouse_env.grid_height:
+            if warehouse_env.grid[new_y][new_x] not in [WALL, SHELF]:
+                return action_id
+
+    # Last resort: try pickup/dropoff
+    return 4 if warehouse_env.robot_carrying is None else 5
+
 
 # Add health check endpoint
 @app.get("/health")

server/app.py

@@ -94,7 +94,7 @@ async def auto_step():
         )
 
 def _get_greedy_action() -> int:
-    """Simple greedy policy: move toward nearest target."""
+    """Simple greedy policy with obstacle avoidance."""
     robot_x, robot_y = warehouse_env.robot_position
 
     # Determine target location
@@ -121,21 +121,72 @@ def _get_greedy_action() -> int:
         if package:
             target_x, target_y = package.dropoff_location
         else:
-            return 4  # Try action
-
-    # Simple pathfinding: move closer on one axis at a time
-    if robot_x < target_x:
-        return 3  # RIGHT
-    elif robot_x > target_x:
-        return 2  # LEFT
-    elif robot_y < target_y:
-        return 1  # DOWN
-    elif robot_y > target_y:
-        return 0  # UP
-    else:
-        # At target location
+            return 5  # Try to drop off
+
+    # Check if at target location
+    if robot_x == target_x and robot_y == target_y:
         return 4 if warehouse_env.robot_carrying is None else 5
 
+    # Try to move toward target, checking for obstacles
+    # Priority: move on axis with larger distance first
+    dx = target_x - robot_x
+    dy = target_y - robot_y
+
+    # List of possible moves in order of preference
+    moves = []
+
+    if abs(dx) > abs(dy):
+        # Prioritize horizontal movement
+        if dx > 0:
+            moves.append((3, robot_x + 1, robot_y))  # RIGHT
+        elif dx < 0:
+            moves.append((2, robot_x - 1, robot_y))  # LEFT
+
+        if dy > 0:
+            moves.append((1, robot_x, robot_y + 1))  # DOWN
+        elif dy < 0:
+            moves.append((0, robot_x, robot_y - 1))  # UP
+    else:
+        # Prioritize vertical movement
+        if dy > 0:
+            moves.append((1, robot_x, robot_y + 1))  # DOWN
+        elif dy < 0:
+            moves.append((0, robot_x, robot_y - 1))  # UP
+
+        if dx > 0:
+            moves.append((3, robot_x + 1, robot_y))  # RIGHT
+        elif dx < 0:
+            moves.append((2, robot_x - 1, robot_y))  # LEFT
+
+    # Add perpendicular moves as fallback
+    if dx == 0 and dy != 0:
+        moves.append((3, robot_x + 1, robot_y))  # RIGHT
+        moves.append((2, robot_x - 1, robot_y))  # LEFT
+    elif dy == 0 and dx != 0:
+        moves.append((1, robot_x, robot_y + 1))  # DOWN
+        moves.append((0, robot_x, robot_y - 1))  # UP
+
+    # Try moves in order until we find a valid one
+    WALL = 1
+    SHELF = 2
+
+    for action_id, new_x, new_y in moves:
+        # Check bounds
+        if 0 <= new_x < warehouse_env.grid_width and 0 <= new_y < warehouse_env.grid_height:
+            # Check if cell is passable
+            if warehouse_env.grid[new_y][new_x] not in [WALL, SHELF]:
+                return action_id
+
+    # If no valid move toward target, try any valid move
+    for action_id, dx, dy in [(0, 0, -1), (1, 0, 1), (2, -1, 0), (3, 1, 0)]:
+        new_x, new_y = robot_x + dx, robot_y + dy
+        if 0 <= new_x < warehouse_env.grid_width and 0 <= new_y < warehouse_env.grid_height:
+            if warehouse_env.grid[new_y][new_x] not in [WALL, SHELF]:
+                return action_id
+
+    # Last resort: try pickup/dropoff
+    return 4 if warehouse_env.robot_carrying is None else 5
+
 
 # Add health check endpoint
 @app.get("/health")