Competence-Aware Path Planning Via Introspective Perception
نویسندگان
چکیده
Robots deployed in the real world over extendedperiods of time need to reason about unexpected failures, learn predict them, and proactively take actions avoid future failures. Existing approaches for competence-aware planning are either model-based, requiring explicit enumeration known failure sources, or purely statistical, using state- location-specific statistics infer competence. We instead propose a structured model-free approach by reasoning plan execution failures due errors perception, without priori sources statistics. introduce competence-aware path via introspective perception (CPIP) , Bayesian framework iteratively exploit task-level competence novel deployment environments. CPIP factorizes problem into two components. First, learned location-agnostic setting xmlns:xlink="http://www.w3.org/1999/xlink">introspective perception prior Second, during actual deployments, prediction is context-aware setting. Experiments simulation show that proposed outperforms frequentist baseline multiple mobile robot tasks, further validated experiments environments with perceptually challenging obstacles terrain.
منابع مشابه
Perception-aware Path Planning
In this paper, we give a double twist to the problem of planning under uncertainty. State-of-the-art planners seek to minimize the localization uncertainty by only considering the geometric structure of the scene. In this paper, we argue that motion planning for vision-controlled robots should be perception aware in that the robot should also favor texture-rich areas to minimize the localizatio...
متن کاملRobust Motion Planning via Perception-Aware Multiobjective Search on GPUs
In this paper we describe a framework towards computing well-localized, robust motion plans through the perception-aware motion planning problem, whereby we seek a low-cost motion plan subject to a separate constraint on perception localization quality. To solve this problem we introduce the Multiobjective PerceptionAware Planning (MPAP) algorithm which explores the state space via a multiobjec...
متن کاملPerception-Aware Motion Planning via Multiobjective Search on GPUs
In this paper we describe a framework towards computing well-localized, robust motion plans through the perception-aware motion planning problem, whereby we seek a low-cost motion plan subject to a separate constraint on perception localization quality. To solve this problem we introduce the Multiobjective PerceptionAware Planning (MPAP) algorithm which explores the state space via a multiobjec...
متن کاملRobust Active Perception via Data-association aware Belief Space planning
We develop a belief space planning (BSP) approach that advances the state of the art by incorporating reasoning about data association (DA) within planning, while considering additional sources of uncertainty. Existing BSP approaches typically assume data association is given and perfect, an assumption that can be harder to justify while operating, in presence of localization uncertainty, in am...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE robotics and automation letters
سال: 2022
ISSN: ['2377-3766']
DOI: https://doi.org/10.1109/lra.2022.3145517