Multi-agent Planning using Visual Language Models

ECAI 2024

wash a tomato and put it on the counter (trial_T20190909_012550_586494)

Ground truth Single Agent with table Multi Agent with table Single Agent with image Multi Agent with image
STEP 1: go to the fridge
STEP 2: take the tomato from the fridge
STEP 3: take the tomato to the sink
STEP 4: wash it in the sink then remove
STEP 5: take the tomato to the counter to the right of the sink
STEP 6: put the tomato on the counter
Turn around and walk to the fridge.,
Take the tomato out of the fridge.,
Turn around and walk to the sink.,
Wash the tomato in the sink.,
Turn around and walk to the counter.,
Place the tomato on the counter.
Turn around and walk to the counter.
Take the tomato from the counter.
Turn around and walk to the sink.
Wash the tomato in the sink.
Turn around and walk to the counter.
Place the washed tomato on the counter.
1. Walk to the tomato on the counter near the sink.
2. Pick up the tomato.
3. Turn to face the sink.
4. Walk to the sink.
5. Turn on the tap.
6. Wash the tomato under the running water.
7. Turn off the tap.
8. Walk to a clear area on the counter.
9. Place the tomato on the counter.
1. Walk to the sink, which is on the counter.
2. Pick up the tomato, which is in the sink.
3. Turn on the faucet, which is above the sink, to wash the tomato.
4. Wash the tomato under the running water from the faucet.
5. Turn off the faucet, which is above the sink.
6. Dry the tomato using a cloth or paper towel (assuming it's within reach or on the counter).
7. Place the washed and dried tomato on the counter, to the right of the sink.
Architecture