Does π0.5 run on AgileX PiPER?

works with caveats

T1 · upstream documentedlast verified 2026-10-25 · todayopenpi

Capabilities

Capability	State	Notes	Evidence
Train / fine-tune	works	Vendor: π0.5 fine-tuning configs pi05_aloha / pi05_aloha_lora for cobot_magic data collected with agilexrobotics/data_tools. Community: LeRobot pi05 checkpoint trained on single-arm Piper data.	ev-openpi-agilex-readme, ev-hub-qualia-pi05
Real-robot inference	works	Vendor: serve the fine-tuned checkpoint with openpi's serve_policy.py and run scripts/aloha_inference-joint-ros2.py against dual PiPER arms.	ev-openpi-agilex-readme, ev-openpi-agilex-configs
Simulation inference	no verified evidence		—
Teleop + record	no verified evidence		—

Caveats

The vendor-documented route is AgileX's own openpi fork (openpi-agilex, JAX, ROS 2) on the bimanual Cobot Magic (two PiPER arms, three cameras), not a single PiPER arm and not LeRobot.
AgileX documents the fine-tuning and inference workflow but publishes no PiPER success rates or released PiPER checkpoint.

Evidence 3 sources; the cell shows the highest tier

T1 · upstream documentedvendor-docssource 2026-02-02verified 2026-10-25 (today)
AgileX's openpi distribution README: fine-tune π0.5 (pi05_base) on your data, serve it with serve_policy.py, then run inference on dual PiPER arms via the provided ROS 2 scripts.
“open your dual piper arms ros-sdk and multi cameras, then”
https://github.com/agilexrobotics/openpi-agilex/blob/432577c37c4fc650fcbea03f03e45f936e9e4a08/README.md
T1 · upstream documentedvendor-docssource 2026-02-02verified 2026-10-25 (today)
Same README's config table maps the π0.5 configs pi05_aloha and pi05_aloha_lora to the inference script for the Cobot Magic (three cameras, two arms).
“| pi05_aloha | scripts/aloha_inference-joint-ros2.py | cobot_magic, 3 cameras and 2 arms |”
https://github.com/agilexrobotics/openpi-agilex/blob/432577c37c4fc650fcbea03f03e45f936e9e4a08/README.md
T3 · community reportedhub-checkpointsource 2026-03-26verified 2026-10-24 (1d ago)
config.json type=pi05; trained on callum-sh/piper-popcorn whose meta/info.json robot_type=piper.
https://huggingface.co/qualia-robotics/pi05-piper-popcorn-6956e853

π0.5 inference speed by hardware robot-independent · inference cost only

Compute	Runtime	Precision	Cams	p50 / p95 ms	Inference	Platform	Source
RTX 4090	llama.cpp	fp16	2 @224x224	51.7 / —	19.34 Hz	— conditions board: NVIDIA RTX 4090 · ggml_cuda_f16_f32_out: 0 (README preset for RTX 4090) Inference cost only; not task success. Full VLM + action-expert pass (ViT + LLM + 10-step action expert), LIBERO inputs (agent-view + wrist at 224x224). From the EagleVLA-Edge README RTX 4090 table (P50), PR #6 configuration. The README's naive π0.5 baseline on this GPU: 162.9 ms (not filed as a separate run: the baseline precision is not stated).	T3 · community reported
RTX 4090	llama.cpp	fp16	2 @224x224	58.5 / —	17.09 Hz	— conditions board: NVIDIA RTX 4090 · ggml_cuda_f16_f32_out: 0 (README preset for RTX 4090) Inference cost only; not task success. Full VLM + action-expert pass (ViT + LLM + 10-step action expert), LIBERO inputs (agent-view + wrist at 224x224). From the EagleVLA-Edge README RTX 4090 table (P50). The README's naive π0.5 baseline on this GPU: 162.9 ms (not filed as a separate run: the baseline precision is not stated).	T3 · community reported
Jetson AGX Thor 128GB	llama.cpp	fp16	2 @224x224	132.8 / —	7.53 Hz	— conditions board: Jetson Thor (paper/README: "Jetson Thor") Inference cost only; not task success. Full VLM + action-expert pass (ViT + LLM + 10-step action expert), LIBERO inputs (agent-view + wrist at 224x224). Later configuration from the EagleVLA-Edge README (PR #6); the README notes an accuracy caveat for the two-switch GEMM preset on Thor. Naive PyTorch π0.5 on the same board per the paper: 457.9 ms (2.18 Hz) (not filed as a separate run: the baseline precision is not stated).	T3 · community reported
Jetson AGX Thor 128GB	llama.cpp	fp16	2 @224x224	202.8 / —	4.93 Hz	— conditions board: Jetson Thor (paper/README: "Jetson Thor") Inference cost only; not task success. Full VLM + action-expert pass (ViT + LLM + 10-step action expert), LIBERO inputs (agent-view + wrist at 224x224). Paper's 'control frequency' (10.25 Hz) is 1/reaction time with VLM-skipping scheduling; not executed actions/s. Board inferred to be the 128 GB T5000 class from the paper's 130 W max-power entry for Thor (T4000 is 40–70 W). Naive PyTorch π0.5 on the same board per the paper: 457.9 ms (2.18 Hz) (not filed as a separate run: the baseline precision is not stated).	T3 · community reported
Jetson AGX Orin 64GB	llama.cpp	fp16	2 @224x224	271.1 / —	3.69 Hz	power_mode 50W (paper label "Orin-50W") conditions board: Jetson Orin, 'Orin-50W' power mode (AGX Orin 64GB inferred, see ev-orin-board-inferred) Inference cost only; not task success. Full VLM + action-expert pass (ViT + LLM + 10-step action expert), LIBERO inputs (agent-view + wrist at 224x224). Later configuration from the EagleVLA-Edge README (time cache + cuBLASLt GEMM tuning, PR #6); not in the paper. Naive PyTorch π0.5 on the same board per the paper: 1420.8 ms (0.70 Hz) (not filed as a separate run: the baseline precision is not stated).	T3 · community reported
Jetson AGX Orin 64GB	llama.cpp	fp16	2 @224x224	374.5 / —	2.67 Hz	power_mode 50W (paper label "Orin-50W") conditions board: Jetson Orin, 'Orin-50W' power mode (AGX Orin 64GB inferred, see ev-orin-board-inferred) Inference cost only; not task success. Full VLM + action-expert pass (ViT + LLM + 10-step action expert), LIBERO inputs (agent-view + wrist at 224x224). Paper's 'control frequency' (6.93 Hz) is 1/reaction time with confidence-based scheduling that skips the VLM; it is not executed actions/s and is not recorded as control_rate_hz. Naive PyTorch π0.5 on the same board per the paper: 1420.8 ms (0.70 Hz) (not filed as a separate run: the baseline precision is not stated).	T3 · community reported
Jetson Orin Nano 8GB (Super)	TensorRT	fp16	2 @640x480	438.47 / 438.93	2.28 Hz	jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10 conditions board: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 6.39 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing.	T3 · community reported
Jetson Orin Nano 8GB (Super)	TensorRT	fp16	3 @640x480	643.39 / 644.92	1.55 Hz	jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10 conditions board: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 6.18 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing.	T3 · community reported

Embed this cell

Badge for READMEs and model cards. It always shows the current state.

[![π0.5 on AgileX PiPER: works with caveats](https://caniembody.pages.dev/badge/agilex-piper/pi05.svg)](https://caniembody.pages.dev/compat/agilex-piper/pi05)

<iframe src="https://caniembody.pages.dev/embed/agilex-piper/pi05" width="380" height="132" style="border:0" title="π0.5 on AgileX PiPER | CanIEmbody"></iframe>

History

2026-10-25 fecccd1 Initial release: robot policy compatibility matrix · Danilo Znamerovszkij