Collaborative online planning for automated victim search in disaster response

Abstract

Collaboration is essential for effective performance by groups of robots in disaster response settings. Here we are particularly interested in heterogeneous robots that collaborate in complex scenarios with incomplete, dynamically changing information. In detail, we consider an automated victim search setting, where unmanned aerial vehicles (UAVs) with different capabilities work together to scan for mobile phones and find and provide information about possible victims near these phone locations. The state of the art for such collaboration is robot control based on independent planning for robots with different tasks and typically incorporates uncertainty with only a limited scope. In contrast, in this paper, we take into account complex relations between robots with different tasks. As a result, we create a joint, full-horizon plan for the whole robot team by optimising over the uncertainty of future information gain using an online planner with hindsight optimisation. This joint plan is also used for further optimisation of individual UAV paths based on the long-term plans of all robots. We evaluate our planner’s performance in a realistic simulation environment based on a real disaster and find that our approach finds victims 25% faster compared to current state-of-the-art approaches

The potential of emergent disruptive technologies for humanitarian supply chains: the integration of blockchain, Artificial Intelligence and 3D printing

“…Nevertheless, the need to reach the affected areas during disaster management despite these challenges has pointed at alternative vehicles, such as UAVs. There are articles looking at providing disaster assessment (Oruc and Kara 2018), developing emergency communication systems (Tuna, Nefzi, and Conte 2014), supporting search and rescue operations (Beck et al 2018), and enhancing distribution (Chowdhury et al 2017). Alternatively, an option to avoid having to transport commodities at all is through on-site production.…”

Aplicaciones practicas de los sistemas multi-UAV y enjambres aéreos

“…En casos de desastres naturales como terremotos o inundaciones, los sistemas multi-UAV también han demostrado ser potencialmenteútiles. En (Beck et al, 2018) se plantea el despliegue de un grupo de UAVs que buscarían de forma autónoma a posibles supervivientes generando trayectoriasóptimas basadas en la señal de los teléfonos móviles personales. Para validar el método propuesto, se estudia su comportamiento en una simulación realista basada en el terremoto que asoló Haití en 2010.…”

Multi-Objective Multi-Agent Planning for Jointly Discovering and Tracking Mobile Objects

“…RFSs are finite-set valued random variables. We assume that each measurement is uniquely identified, e.g., transmit frequencies from radio beacons (Cliff et al 2015; Kays et al 2011;Nguyen et al 2019a;2019b;Thomas, Holland, and Minot 2012) or MAC address (Beck et al 2018;Charrow, Michael, and Kumar 2015), which is typical for wildlife tracking or search and rescue missions. Since each object is uniquely identified, we propose using a the multisensor Bernoulli filter (MS-BF) (Vo et al 2012), where each object's state is a Bernoulli RFS, and run multiple MS-BF filters parallelly to track multiple objects.…”

“…Such problems are ubiquitous in wildlife tracking (Cliff et al 2015;Kays et al 2011;Nguyen et al 2019a;Thomas, Holland, and Minot 2012), search and rescue missions (Gerasenko et al 2001;Murphy et al 2008). For instance, a team of unmanned aerial vehicles (UAVs) can be deployed to monitor activities of endangered radio-tagged wildlife in a survey scene, or to search for victims in a disaster response (Beck et al 2018). Hence, it is critical to not only search for undiscovered objects but also track the movements of discovered objects of interest.…”