Sort six blocks into three containers, one of them a drawer (one uncalibrated camera, low-level control)

A two-finger parallel gripper hangs over a table (a floating gripper, no arm; it cannot rotate). x points to the right as seen from the front of the table, y away from the front (toward the back of the table), z up; the table top is at z = 0 and spans x from -0.35 to 0.35 and y from -0.30 to 0.30. The gripper's tool point can reach x in [-0.34, 0.34], y in [-0.27, 0.28], z in [0.012, 0.35]. The fingers close along the y axis; the fully open gap is 10 cm.

Goal: Six blocks lie on the table: two red, two blue, two green. Put both red blocks into the drawer of the cabinet and close the drawer (within 1 cm), put both blue blocks into the white bowl, and both green blocks into the grey tray. The drawer cabinet stands at the back right. Its drawer slides out toward the front (toward -y) by up to 12 cm; its handle is a horizontal bar along x, about 4 cm in front of the drawer face and 4.5 cm above the table. The fingers can close around the bar from above if the gripper is only partly open (e.g. grip 0.2; a fully open gripper hits the drawer face). The drawer's inside is about 11.8 cm square with 5 cm high walls.

What you can observe

robo observe does not give object or goal positions. It returns only hand_pos, gripper_open, constraint_violations and saves one image per camera (front; 320 x 320 pixels), printing the paths. Open the images to see the scene. hand_pos is the gripper's tool point (between the fingertips) in metres, gripper_open is 0 (closed) to 1 (10 cm gap) (there is no contact sensor that says what the fingers hold: a finger opening above zero after closing means something is between them, and the images show what), and constraint_violations lists broken rules (any entry means the task has failed).

There is only one camera, and robo info does NOT give its projection matrix (only its image size and field of view). You know where the gripper is from hand_pos, so you can relate image positions to world positions by moving the gripper and looking where it appears.

Gripper

The grip value is a finger position target, not a hold command: +1 = fully closed, -1 = fully open (10 cm gap), and values in between give a partial opening (finger gap = 10 cm * (1 - G) / 2, so 0 = half open, a 5 cm gap). There is no separate "hold" value: to keep holding an object, keep sending +1 (the fingers then squeeze it). robo move-to X Y Z --grip G applies G on every step of the move, starting with the first, so --grip 1 closes the fingers at the start of the move (they take about 15 steps to close fully); without --grip, the last grip value is kept. robo grip G --steps N holds the hand still for N steps while applying G. The same values apply to the GRIP argument of robo act.

Task rules

• Skills are disabled on this task: robo move-to and robo grip return an error. Use robo act DX DY DZ GRIP only (DX/DY/DZ move the tool point by about 1 cm per unit per step; GRIP +1 closes, -1 opens, values in between give a partial opening: finger gap = 10 cm * (1 - GRIP) / 2).
• robo act --repeat N is limited to N <= 10 on this task (larger values are cut to 10).
• Step budget: 1750 simulated steps (one step = 20 ms). Wall-clock limit: 30 minutes.
• Objects must be released (not touching the fingers) when the episode is judged, about 10 steps after robo done.