xlang-ai/OSWorld
OSWorld is a benchmarking platform for evaluating multimodal AI agents performing open-ended tasks in real computer environments using virtual machines and various virtualization technologies.
Awesome AI Agents › Sensor Fusion Agents
karanchawla/GPS_IMU_Kalman_Filter
This project implements an Extended Kalman Filter (EKF) designed to fuse data from multiple sensors including GPS, IMU (Inertial Measurement Unit), and encoder readings to accurately estimate the pose of a ground robot within a navigation frame. The EKF is a sophisticated algorithm that extends the traditional Kalman Filter to handle non-linear state transition and observation models by linearizing them around the current state estimate using Jacobian matrices. This approach allows the filter to predict the robot's state and update it based on noisy sensor measurements, assuming the process and observation noises are zero-mean Gaussian with known covariance. The project specifically addresses the fusion of velocity data from encoders or GPS velocity sensors, yaw rate from a yaw rate sensor, and longitudinal acceleration from an accelerometer, along with positional data from GPS. By integrating these diverse sensor inputs, the EKF provides a robust and accurate estimation of the robot's position and orientation (pose) over time, which is critical for navigation and control in robotics. The repository includes detailed explanations of the mathematical foundations of the EKF, including the state transition and observation models, the role of the Jacobian matrices in linearizing non-linear functions, and the noise assumptions. Visual aids such as diagrams of the EKF step and the ground robot model help in understanding the implementation and application context. This project is valuable for robotics researchers and engineers working on autonomous ground vehicles, sensor fusion, and state estimation. It leverages well-established concepts from probabilistic robotics and provides practical insights and references for further learning. The implementation can be used as a foundation for developing advanced navigation systems that require precise and reliable pose estimation from multiple sensor modalities.
https://github.com/karanchawla/GPS_IMU_Kalman_Filter
Also in Sensor Fusion Agents
IBM/AssetOpsBench
Open IBM framework and benchmark for building, orchestrating and evaluating domain-specific AI agents in industrial asset operations, with MCP servers over sensors, failure modes, time series and work orders.
web-arena-x/webarena
WebArena is a self-hostable web environment designed for building and evaluating autonomous agents capable of realistic web navigation and interaction tasks.
google-deepmind/android_env
AndroidEnv is a Python library by DeepMind that provides a Reinforcement Learning platform by simulating Android devices, enabling agents to interact with real-world Android applications through touchscreen gestures for diverse RL tasks.
google-research/android_world
AndroidWorld is a comprehensive environment and benchmark for autonomous agents to interact with and control Android devices through a live emulator, featuring diverse tasks and integration with web-based benchmarks.
OSU-NLP-Group/TravelPlanner
TravelPlanner is a benchmark for evaluating language agents in real-world travel planning tasks involving complex tool use and multiple constraints.
StonyBrookNLP/appworld
AppWorld is a high-fidelity execution environment simulating a world of apps and people to benchmark and evaluate interactive coding agents through diverse and challenging autonomous tasks.
nottelabs/open-operator-evals
Open-operator-evals is an open-source benchmarking framework that evaluates the performance of web operators and agents using multiple metrics and a reproducible dataset to provide transparent and statistically sound comparisons.