hud-evals/pi05-AssembleBench-12k

pi0.5 AssembleBench - BC baseline (12k)

Behavior-cloning baseline for AssembleBench: pi0.5 supervised-finetuned on all 14 tasks for 12k steps. This is the full-suite reference number in the writeup.

pi0.5 finetuned for AssembleBench, a 14-task contact-rich robot assembly benchmark on the NIST ATB-1 taskboard: insert round and square pegs, mesh gears, thread nuts. Built on Isaac Lab Arena with the DROID robot platform (Franka Panda + Robotiq 2F-85).

Read the writeup: Benchmarking Robot Models on Contact-Rich Assembly.

Usage

git clone https://github.com/hud-evals/assemble-bench.git
cd assemble-bench
pip install -r examples/requirements.txt

# Serve the simulator (see the repo README for the Isaac Sim install)
OMNI_KIT_ACCEPT_EULA=YES python -m hud.environment.server env.py --port 8765

# Evaluate this checkpoint
python examples/run_eval.py --task peg_round_16mm --checkpoint hud-evals/pi05-AssembleBench-12k

The DROID input/output convention is not baked into the checkpoint. examples/pi05_agent.py carries the adapter: front and wrist RGB resize-padded to 224, an 8-D state of 7 joint positions plus gripper, and 8-D absolute joint-target actions at 15 Hz with a binarized gripper.

Training

Finetuned from DAVIAN-Robotics/pi05_droid_jointpos (full finetune, VLM included) on hud-evals/AssembleBench, 1355 synthetic demonstrations generated by scripted experts reading privileged simulator state, with no teleoperation.

Supervised finetuning for 12,000 steps across all 14 tasks.

Limitations

Task-specific: this is not a generalist checkpoint, and it is trained purely in simulation. Success on these tasks is sparse - a handful of wins out of thirty on the harder families - so the writeup reports dense reward alongside binary success. Square pegs and small gears remain close to zero.

Related checkpoints

Checkpoint	What it is
pi05-AssembleBench-12k	behavior-cloning baseline, all 14 tasks
pi05-AssembleBench-cgdagger-r3	BC + 3 rounds of code-gated DAgger, the final checkpoint