Python package for the evaluation of odometry and SLAM

CLI-first QA toolkit for point clouds, trajectories, and 3D perception outputs. Evaluate map post-processing, SLAM runs, and geometry regressions with reports, gates, and web inspection.

Resources for SiTAR, a situated trajectory analysis system for AR which provides in-the-wild pose error estimates

Timestamp Align between the trajs. from VICON & Estimated from Algo.

Toolkits for trajectory alignment and evaluation

6-DoF ego-motion estimation in CARLA using RGB-D visual odometry — ORB features, PnP-RANSAC, and ATE evaluation

End-to-end agent evaluation — trajectory eval, tool-use correctness, cost-per-task, latency budgets, regression suites with golden trajectories, LLM-as-judge with calibration. For full agent runs, not just classifiers.

Sanity checks for using small VLM rerankers (Qwen3‑VL 2B) to score candidate driving trajectories from natural‑language instructions.

🌟 Develop EvoToken-DLM, an innovative language model enhancing diffusion with soft token distributions for improved performance and flexibility.

Build OR optimization models with Openpangu-7B, supporting fine-tuning, automated modeling, constraint generation, and variable pruning