Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2608.09892

XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment

XPolicyLab Community·Tianxing Chen·Yue Chen·Tian Nian·Zijian Cai·Guangyu Chen·Wenwei Lin·Qiwei Liang·Zanxin Chen·Peicheng Xiang·Kailun Su·Zixuan Li·Junyuan Tang·Yan Qin·Qiangyu Chen·Shaolong Zhu·Tengyue Jiang·Yiqing Wang·Xiang Li·Jiahao Zhang·Weijie Wan·Baijun Chen·Honghao Su·Kehe Ye·Shujia Liu·Kaixuan Wang·Haotian Liang·Yunze Liu·Mingleyang Li·Yuran Wang·Boyu Chen·Hongzhe Bi·Shuhe Huang·Hengkai Tan·Jisong Cai·Yao Mu·Jun Guo·Xiaofeng Wang·Zheng Zhu·Weijie Ke·Hengtao Li·Yuhang Tang·Xiaofan Li·Ganlin Yang·Zhangzheng Tu·Shuai Yang·Wenxuan Song·Pengxiang Ding·Kaidong Zhang·Yu Sun·Junliang Guo·Tong Zhang·Yixing Chen·Rongxu Cui·Zongzheng Zhang·Haoxiang Ma·Junhao Cai·Haoyu Zhang·Senqiao Yang·Jinhui Ye·Pengguang Chen·Shu Liu·Xiu Su·Wenhan Fang·Wenhao Li·Yichao Cao·Chengyao Wang·Qiang Chen·Ping Luo·Wenbo Ding
View original source ↗Read source document ↗Export metadata ↓

Abstract

Robot policy evaluation and deployment remain fragmented by model-specific software dependencies, data representations, and runtime interfaces, so that connecting N policies to M evaluation environments requires O(NM) separate integrations. We present XPolicyLab, a unified standard and open ecosystem that reduces this cost to O(N+M). XPolicyLab specifies common observation, action, and trajectory schemas together with a minimal adapter interface for observation updates, action prediction, batched execution, and episode reset, while a dependency-isolated client/server architecture separates policy inference from environment execution, so that each side retains its native software stack and may run locally or remotely. The ecosystem integrates 42 robot policies and standardizes their installation, debugging, serving, and evaluation workflows. Across these adapters, model-specific code varies by an order of magnitude while the environment-facing loop stays within a few lines of a fixed reference, confirming that the contract confines heterogeneity to the policy side. In a controlled study, conforming to the standard reduces the integration effort of a representative policy from over five hours to two hours, and packaged agent skills reduce it further to thirty minutes. The same adapters serve RoboTwin, RoboDojo simulation, and standardized real-robot evaluation through one interface. XPolicyLab is released as shared infrastructure for reproducible policy comparison and standardized deployment across simulation and physical platforms. Project website: https://xpolicylab.github.io/.

Explore related subjects

cs.RO

Keep this discovery

BibTeXRIS

XPolicyLab Community, Tianxing Chen, Yue Chen, Tian Nian, Zijian Cai, Guangyu Chen, Wenwei Lin, Qiwei Liang, Zanxin Chen, Peicheng Xiang, Kailun Su, Zixuan Li, Junyuan Tang, Yan Qin, Qiangyu Chen, Shaolong Zhu, Tengyue Jiang, Yiqing Wang, Xiang Li, Jiahao Zhang, Weijie Wan, Baijun Chen, Honghao Su, Kehe Ye, Shujia Liu, Kaixuan Wang, Haotian Liang, Yunze Liu, Mingleyang Li, Yuran Wang, Boyu Chen, Hongzhe Bi, Shuhe Huang, Hengkai Tan, Jisong Cai, Yao Mu, Jun Guo, Xiaofeng Wang, Zheng Zhu, Weijie Ke, Hengtao Li, Yuhang Tang, Xiaofan Li, Ganlin Yang, Zhangzheng Tu, Shuai Yang, Wenxuan Song, Pengxiang Ding, Kaidong Zhang, Yu Sun, Junliang Guo, Tong Zhang, Yixing Chen, Rongxu Cui, Zongzheng Zhang, Haoxiang Ma, Junhao Cai, Haoyu Zhang, Senqiao Yang, Jinhui Ye, Pengguang Chen, Shu Liu, Xiu Su, Wenhan Fang, Wenhao Li, Yichao Cao, Chengyao Wang, Qiang Chen, Ping Luo, Wenbo Ding. 2026-08-10. XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment. https://arxiv.org/abs/2608.09892

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in $\pi_{0.5}$. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to $\pi_{0.5}$, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains $\pi_{0.5}$'s robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming $\pi_{0.5}$ on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

cs.RO↗
arXiv2026

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

Imitation learning has achieved impressive results in robotic manipulation, yet most existing approaches assume clean backgrounds and lack explicit mechanisms for obstacle-aware motion generation. Extending such policies to cluttered, real-world scenes with unstructured obstacles remains a key generalization challenge. We present ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder. ObstaDiff extracts a structured target-obstacle-background representation, enabling the downstream alignment policy to generate end-effector trajectories toward a target-centered bottleneck pose while reasoning about surrounding obstacles. We evaluate ObstaDiff on 61 real-robot greenhouse trials per method (366 executions in total). ObstaDiff achieves 75.41% average task success and 8.20% average obstacle collision rate, outperforming representative imitation-learning baselines and improving generalization in cluttered agricultural scenes.

cs.RO↗
arXiv2026

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.

cs.RO↗