Course / Lectures / Lecture 19 / Lab Lab 19

Ground, plan, shield, monitor.

One instruction, one tabletop, one deterministic planner. Parse the sentence, ground the objects, plan with preconditions and effects, execute the plan, and watch the monitor catch what the planner cannot.

5 objects 2 safety rules 4 outcomes + refusal No install · runs in the browser

The pick-and-place lab

World · top-down tabletopthe arm and the held object are drawn at the gripper
A top-down tabletop with a red cube, a red sphere, a blue cube in a bowl, and a knife. A gantry arm moves objects.
Reset. Correct detector, shield off. Press Plan.

Legend. The dashed orange ring is the grounded object; after execution, a dashed red ring marks the intended referent when it differs. The orange path in the trace is the plan; objects in the bowl are drawn inside it. The arm moves on each executed action.

Instruction

Grammar: put the [colour] cube|sphere|knife in the bowl. The parser is deliberately small; a parse failure is a real failure mode.

Perception
Shield

The Knife preset is the unsafe case: with the shield off, the plan grasps the knife and puts it in the bowl. With the shield on, no safe plan exists.

Parse

—

Grounding

Candidates are movable objects; score = colour confidence × shape confidence.
objectcolourshapescorematch
Press Plan.

Plan

    No plan yet.

    Monitor

    Goal, preconditions, and the two safety rules are checked separately.
    checkstatusdetail
    goal—not executed
    preconditions—not executed
    S1 · no sharp grasp—not executed
    S2 · no sharp object in bowl—not executed
    verdict—not executed

    Trace

    Reset. Correct detector, shield off. Press Plan.
    WHAT TO NOTICE

    Two failures the success metric hides.

    CASE 01 · WRONG GROUNDING

    A valid plan for the wrong symbol

    Choose the swapped detector and run the red-cube instruction. The parser is right, the plan is valid, every precondition holds, and the robot puts the sphere in the bowl. The goal over the cube is false. The first divergence is grounding, and the planner cannot see it.

    CASE 02 · UNSAFE PLAN

    Goal achieved, safety violated

    Type “put the knife in the bowl” with the shield off. The plan clears the bowl, grasps the knife, and places it. The goal holds. The monitor reports S1 and S2 violations. This is an unsafe success: the metric says yes and the trace says no.

    CASE 03 · SHIELD ON

    Refusal is an outcome

    Run the same knife instruction with the shield on. The proposed plan is rejected, the shielded search finds no plan, and the system refuses. It does not silently drop the goal or relax the specification. Refusal is the correct result when every safe plan is excluded.

    What the lab is not

    It is a hand-built five-object tabletop with a deterministic breadth-first planner, a toy parser, a simulated detector, and two safety rules. It has no learned perception, no continuous motion planning, no physics, and no real controller. It does not measure a benchmark. It isolates one mechanism: a plan is only as good as its symbols, and safety is a separate claim from success.

    Read the three layers again · Read the grounding section · Read the shielding section · Slides