The MMP: A Mixed-Initiative Mission Planning System for the Multi-Aircraft Domain
نویسندگان
چکیده
The Universität der Bundeswehr München is conducting research in the field of single-operator multi-aircraft guidance. This article describes the Mixed-initiative Mission Planner (MMP) as far as requirements, concept, design and implementation are concerned. The MMP is applied to a timeconstrained multi-aircraft in-flight mission planning problem. It works in conjunction with a cognitive assistant system for an Uninhabited Aerial Vehicle (UAV) operator, who generates and modifies multi-aircraft mission plans incrementally. The assistant system is able to evaluate, complete, and generate such plans with the aid of the MMP and to communicate with the operator, which results in a mixedinitiative planning approach. Mixed-initiative planning systems need to be able to evaluate the partial or complete human plans as well as the problem itself. For this reason there are two instances of the MMP in our system design. One is configured as a slave to the human input to assume what the human is planning and the other as a free planner that generates reference plans. The assumed human plan includes temporal information about already planned and future tasks, and it can be compared to the reference plan by the assistant system, allowing it to decide whether and when to take initiative. The MMP prototype implementation consists of a Planning Process Manager that dynamically generates problem descriptions, a freely available PDDL 2.2 compatible planner, and multiple domain descriptions.
منابع مشابه
Mixed-Initiative Planning in Space Mission Operations
The MAPGEN system represents a successful mission infusion of mixed-initiative planning technology. MAPGEN was deployed as a mission-critical component of the ground operations system for the Mars Exploration Rover mission. Each day, the ground-planning personnel employ MAPGEN to collaboratively plan the activities of the Spirit and Opportunity rovers, with the objective of achieving as much sc...
متن کاملCentralized Path Planning for Multi-aircraft in the Presence of Static and Moving Obstacles
This article proposes a new approach for centralized path planning of multiple aircraft in presence of the obstacle-laden environment under low flying rules. The problem considers as a unified nonlinear constraint optimization problem. The minimum time and control investigate as the cost functions and the maximum velocity and power consider as the constraints. The pseudospectral method applies ...
متن کاملIntegrating Agent-Based Mixed-Initiative Control with an Existing Multi-Agent Planning System
One of the less appreciated obstacles to scaling multi-agent systems is understanding the impact of the role(s) that people will play in those systems. As we try to adapt existing software tools and agent-based applications to play supportive roles in larger multi-agent systems, we must develop strategies for coordinating not only the problem solving behavior of these agent communities, but als...
متن کاملMixed-Initiative Planning in MAPGEN: Capabilities and Shortcomings
MAPGEN (Mixed-initiative Activity Plan GENerator) is a mixed-initiative system that employs automated constraint-based planning, scheduling, and temporal reasoning to assist the Mars Exploration Rover mission operations staff in generating the daily activity plans. This paper describes the mixed-initiative capabilities of MAPGEN, identifies shortcomings with the deployed system, and discusses o...
متن کاملA mixed integer linear programming formulation for a multi-stage, multi-Product, multi-vehicle aggregate production-distribution planning problem
In today’s competitive market place, companies seek an efficient structure of supply chain so as to provide customers with highest value and achieve competitive advantage. This requires a broader perspective than just the borders of an individual company during a supply chain. This paper investigates an aggregate production planning problem integrated with distribution issues in a supply chain ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011