This article presents a robust quaternion left-invariant extended Kalman filter (LI-EKF) for attitude estimation, integrated with an adaptive noise covariance estimation algorithm using an iterative expectation-maximization (EM) approach. The proposed method can effectively estimate both process and measurement noise covariances, enabling the filter to adapt to time-varying noise characteristics and improve attitude estimation accuracy and robustness.
WeHelp, a shared autonomy system, aims to assist wheelchair users with daily tasks by enabling them to control a robot or receive remote assistance from a caregiver.
The key objective is to plan the trails of a robot team in a hazardous environment to maximize the expected team reward and the expected number of surviving robots, which are inherently conflicting goals.
本文提出了一種基於投影的下一最佳視角規劃框架,能夠以極快的速度選擇下一個最佳視角,同時確保物體的完整掃描。
소음 환경에서도 강인한 음향 기반 실내 매핑 시스템을 제공하는 기계 학습 프레임워크를 제안한다.
ロボットの音響センサを使用して環境の空間マップを生成するための機械学習フレームワークを提案する。
The proposed projection-based next-best-view planning framework can efficiently and completely reconstruct unknown 3D objects by replacing computationally expensive ray-casting with a fast projection-based viewpoint quality evaluation.
A machine learning-based framework that enhances the performance of traditional echolocation mapping techniques, enabling reliable acoustic reflector mapping even in highly noisy environments.
Integrating visual, physical, temporal, and geometric representations improves the robustness and generalizability of behavior cloning for effective food acquisition in assistive robotics.
A low-cost, easily reproducible robot learning framework that enables deployable imitation learning on industrial-grade robots, achieving multi-task generalization with simple network architectures and fewer demonstrations than previously thought necessary.