本稿では、従来の拡散モデルの課題を克服し、リアルタイム性能と多様な運転行動生成能力を両立させた、エンドツーエンド自動運転のための新しい生成型意思決定モデルDiffusionDriveを提案する。
This paper introduces SplatR, a novel framework that leverages 3D Gaussian Splatting as a world model for Embodied AI agents to solve experience goal visual rearrangement tasks by enabling consistent view comparisons and robust change detection.
This research proposes a novel hierarchical framework for robot skill transfer, enabling robots to generalize complex manipulation skills to new scenarios by leveraging a knowledge graph-based skill library, adaptive trajectory planning, and tactile perception for real-time adjustments.
DART-LLM is a novel system that leverages large language models (LLMs) to improve multi-robot task decomposition and execution by incorporating dependency awareness, enabling efficient parallel execution and collaboration in complex scenarios.
This paper proposes a novel Model Predictive Control (MPC) approach with Coverage Constraints (CCs) for solving the Weighted Coverage Path Planning (WCPP) problem, enhancing its effectiveness by initializing the solver with a TSP-based heuristic.
본 논문에서는 포화 슬라이딩 모드 제어(SMC)와 지연 보상기를 기반으로 한 강력한 제어 시스템을 설계하여 불확실성을 지닌 공대공 미사일 시스템의 성능을 향상시키는 방법을 제시합니다.
This paper presents the design and simulation of a robust saturated sliding mode controller (SMC) for a pitch-controlled missile, effectively addressing challenges posed by time-varying parameters like thrust, mass, and center of gravity, while also considering actuator limitations and sensor noise.
본 논문에서는 우주 탐사용 다족 로봇의 그리퍼가 입상 물질에서 보행 시 발생하는 침하 현상을 실험 및 시뮬레이션을 통해 분석하고, 이를 통해 로봇의 이동 제어 알고리즘 개선에 기여할 수 있는 방안을 제시합니다.
This research paper presents a novel dynamic programming approach for optimizing UAV path planning to observe multiple objects while adhering to specific observation quality constraints, ensuring both efficient coverage and high-quality data acquisition.
본 논문에서는 실제 비행 역학과 단순화된 설계 모델 간의 불일치를 해결하는 강력한 슬라이딩 모드 제어기를 사용하여 공대공 미사일의 받음각을 제어하는 방법을 제시합니다.