Implementation of survivor detection strategies using drones

Shetty, Sarthak J.; Ravichandran, Rahul; Tony, Lima Agnel; Abhinay, N. Sai; Das, Kaushik; Ghose, Debasish

doi:10.1016/b978-0-12-820276-0.00023-6

Cited by 6 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though the decision making time of the WBE model is greater than the lawnmower model, the WBE model requires fewer number of iterations to locate the survivor. In [7], this WBE model was further developed by devising a set of equations for assigning the weights to the environment coordinates for prioritization. These equations are presented below:…”

Section: The Basic Weight-based Exploration Model and Extensionsmentioning

confidence: 99%

“…Due to the differential assignment of weights to the coordinates, a color gradient can be observed across the quadrants in the Density of Weight Map, which translates to a variation in exploration priority in the Priority of Waypoints Map in Figure 3. This improved model was then used to locate survivors in multiple simulated environments and survivor configurations using Gazebo and ROS [7]. The resulting survivor search-times for the WBE (T W ) and lawnmower (T L ) models are presented in Table 2.…”

Section: The Basic Weight-based Exploration Model and Extensionsmentioning

confidence: 99%

“…The survivor search times of the WBE model were compared to that of a standard lawnmower model, in a 10 m x 10 m area with the survivor located at the the 5 m x 5 m mark. While the lawnmower model required a total of 261 seconds to locate the survivor, the WBE model took 149 seconds, an improvement of 75% [7]. Given the improvement in performance of the WBE model, we adapted the WBE model to run on a team of UAVs, involved in locating multiple survivors in the given environment.…”

Section: The Basic Weight-based Exploration Model and Extensionsmentioning

confidence: 99%

“…In recent years, several technological solutions, in areas such as dynamic routing of resources [1] and monitoring of fast flowing waters [2], have been proposed to mitigate the effects of such natural disasters [3], [4]. Given their ability to rapidly traverse large areas affected by fast moving flood waters, UAVs are becoming increasingly popular as an aid in rescue and monitoring efforts [5], [6], [7]. During rescue efforts, UAVs traditionally use the exhaustive lawnmower search pattern to explore a given area for survivors.…”

Section: Introductionmentioning

confidence: 99%

“…In [6], a Weight-Based Exploration (WBE) model, which leverages valuable information regarding the survivor, as conveyed by on-ground observers, was described to generate a prioritized list of waypoints for exploration to aid the UAV in its search for survivors. This WBE model reduces the time taken by the UAV to locate survivors by nearly 215% in Gazebo simulations and 75% in physical testing, in comparison to the lawnmower model, using an off-the-shelf UAV [7].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Weight-Based Exploration for Unmanned Aerial Teams Searching for Multiple Survivors

Shetty¹,

Ghose²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

During floods, reaching survivors in the shortest possible time is a priority for rescue teams. Given their ability to explore difficult terrain in short spans of time, Unmanned Aerial Vehicles (UAVs) have become an increasingly valuable aid to search and rescue operations. Traditionally, UAVs utilize exhaustive lawnmower exploration patterns to locate stranded survivors, without any information regarding the survivor's whereabouts. In real life disaster scenarios however, on-ground observers provide valuable information to the rescue effort, such as the survivor's last known location and heading. In earlier work, a Weight Based Exploration (WBE) model, which utilizes this information to generate a prioritized list of waypoints to aid the UAV in its search mission, was proposed. This approach was shown to be effective for a single UAV locating a single survivor. In this paper, we extend the WBE model to a team of UAVs locating multiple survivors. The model initially partitions the search environment amongst the UAVs using Voronoi cells. The UAVs then utilize the WBE model to locate survivors in their partitions. We test this model with varying survivor locations and headings. We demonstrate the scalability of the model developed by testing the model with aerial teams comprising several UAVs.

show abstract

Section: The Basic Weight-based Exploration Model and Extensionsmentioning

confidence: 99%

Section: The Basic Weight-based Exploration Model and Extensionsmentioning

confidence: 99%

Section: The Basic Weight-based Exploration Model and Extensionsmentioning

confidence: 99%