Adaptive Path Planning for Autonomous UAV Oceanic Search Missions

Rubio, Juan Carlos García; Vagners, Juris; Rysdyk, Rolf

doi:10.2514/6.2004-6228

Cited by 51 publications

(35 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Candidate sub-flights are given 1.0 unit of reward for every second spent within the task area for up to s seconds. Fly-Through 1 Returns a fixed reward when candidate sub-flights fly within it at all. Equivalent to a Sampling task configured with a very small value of s.…”

Section: Task Type Reward Function Coveragementioning

confidence: 99%

See 1 more Smart Citation

A hierarchical flight planner for sensor-driven UAV missions

Clark

Goodrich

2013

2013 Ieee Ro-Man

View full text Add to dashboard Cite

Abstract-Unmanned Aerial Vehicles (UAVs) are increasingly becoming economical platforms for carrying a variety of sensors. Building flight plans that place sensors properly, temporally and spatially, is difficult. The goal of sensor-driven planning is to automatically generate flight plans based on desired sensor placement and temporal constraints. We present a hierarchical sensor-driven flight planning system capable of generating 2D flights that satisfy desired sensor placement and complex timing and dependency constraints. The system makes use of several well-known planning algorithms and includes a user interface. Results demonstrate that the algorithm is general enough for use by a human in several simulated wilderness search and rescue scenarios. In order to accomplish a task using UAV-mounted sensors, the UAV's flight path must place the relevant sensors effectively both temporally and spatially. A camera, for example, should be positioned so that targets are visible within the frame. Often, this is accomplished by a human operator flying remotely or by an autopilot flying a series of waypoints, although there exist algorithms for placing specific sensors at specific locations for specific applications [8]- [10]. Planning (or remotely flying) a path that places sensors effectively isn't easy. This means that, often, the operator must imagine himself or herself in the position of the plane and then take into account a variety of factors including sensor properties (field of view, useful range) and UAV kinematics (airspeed, turning radius). I. INTRODUCTIONCurrent algorithms are either difficult, error-prone, require a high level of attention from operators or they are specific to particular applications and particular sensors. We propose a general approach to planning that is based on a belief that users with minimal training can be empowered to easily create sophisticated flight plans by expressing their highlevel sensor goals and constraints to a planning program (see Figure 1). We call this process sensor-driven planning. This paper presents both a user interface for specifying flight goals and constraints as well as a general-purpose algorithm for generating flight plans that accomplish the goals while satisfying the constraints.

show abstract

Section: Task Type Reward Function Coveragementioning

confidence: 99%

“…UAVs are capable of carrying a wide variety of sensors, including the following: cameras (visible [1], [2] and other spectrums [3]), radio antennas, laser range finders [4], radars [5], and radiation [6] and chemical [7] detectors.…”

Section: Introductionmentioning

confidence: 99%

A hierarchical flight planner for sensor-driven UAV missions

Clark

Goodrich

2013

2013 Ieee Ro-Man

View full text Add to dashboard Cite

show abstract

“…For additional material see [6], [7], [8], [9], and [10]. Difficulties with these strategies are: they require extensive computational power (evolutionary algorithms [4], [11], are limited to generating simple paths (convex optimization techniques [5]), and many other open problems.…”

Section: Original Set Of Arcs (Edges) In Networkmentioning

confidence: 99%

Time constrained randomized path planning using spatial networks

Lum

Rysdyk²

2008

2008 American Control Conference

Self Cite

View full text Add to dashboard Cite

Abstract-Real time planning of optimal paths remains an open problem in many applications of autonomous systems. This paper demonstrates a computationally efficient method for generating a set of feasible paths through parameterization into a series of nodes. The nodes and the arcs make up a directed graph. The state of the environment is embedded in an occupancy based map. A notion of optimality is introduced by combining the directed graph with this map. Network optimization techniques are used to find the best path through the directed graph.

show abstract

“…A number of multiple UAV path planning algorithms have been developed using market-based approaches [24], dynamic programming [25], evolutionary computation [26], probability maps [27], and MILP [28]. Salva et al [29] presents an area coverage strategy where the UAVs distribute the areas to cover among themselves and loiter around the area.…”

Section: Introductionmentioning

confidence: 99%

Multiple UAV exploration of an unknown region

Sujit

Beard

2008

Ann Math Artif Intell

View full text Add to dashboard Cite

In this paper, we present an exploration system for multiple unmanned aerial vehicles (UAVs) navigating through a simulated unknown region that contains obstacles of unknown shape, size, and initial position. The UAVs have to explore and monitor the region continuously. The UAVs have limited sensor and communication ranges and kinematic constraints. The environment may have blind alleys that may cause the UAV to collide with an obstacle. Since the UAVs have limited sensor range, they cannot detect whether the alleys lead to an obstacle or not. Due to the presence of multiple agents and kinematic constraints, the UAVs have to cooperate with each other in selecting their paths, otherwise they may collide with each other. The physical and sensor constraints on the UAVs, coupled with uncertainty in the environment makes the problem of multiple UAVs exploring the unknown region a difficult problem. We developed an exploration system that uses (a) an exploration algorithm to generates safe paths for travel in narrow corridors and (b) a dynamic leader selection scheme to take the presence of multiple agents into account. We also determine the minimum communication range required to ensure no collisions occur inside the narrow corridors. Monte-Carlo simulation were carried out to analyze the effect on area coverage with changes in number of agents, sensor range, and communication range.

show abstract

Adaptive Path Planning for Autonomous UAV Oceanic Search Missions

Cited by 51 publications

References 10 publications

A hierarchical flight planner for sensor-driven UAV missions

A hierarchical flight planner for sensor-driven UAV missions

Time constrained randomized path planning using spatial networks

Multiple UAV exploration of an unknown region

Contact Info

Product

Resources

About