Jens Wawerla

HRI in the sky: Creating and commanding teams of UAVs with a vision-mediated gestural interface

Extending our previous work in real-time vision-based Human Robot Interaction (HRI) with multi-robot systems, we present the first example of creating, modifying and commanding teams of UAVs by an uninstrumented human. To create a team the user focuses attention on an individual robot by simply looking at it, then adds or removes it from the current team with a motion-based hand gesture. Another gesture commands the entire team to begin task execution. Robots communicate among themselves by wireless network to ensure that no more than one robot is focused, and so that the whole team agrees that it has been commanded. Since robots can be added and removed from the team, the system is robust to incorrect additions. A series of trials with two and three very low-cost UAVs and off-board processing demonstrates the practicality of our approach.

A fast and frugal method for team-task allocation in a multi-robot transportation system

In this paper we present two task-allocation strategies for a multi-robot transportation system. The first strategy is based on a centralized planner that uses domain knowledge to solve the assignment problem in linear time. In contrast in the second strategy, individual robots make rule-based allocation decisions using only locally obtainable information and single value communication. Both methods are tested and analysed in simulation experiments. We show that the rule-based method performs well but the lack of information has to be paid for with increased energy consumption.

Potential of a low‐cost sensor network to understand the spatial and temporal dynamics of a mountain snow cover

The spatial and temporal dynamics of seasonal snow covers play a critical role for many hydrological, ecological, and climatic processes. This paper presents a new, innovative approach to continuously monitor these dynamics using numerous low-cost, standalone snow monitoring stations (SnoMoS). These stations provide snow and related meteorological data with a high temporal and spatial resolution. Data collected by SnoMoS include: snow depth, surface temperature, air temperature and humidity, total precipitation, global radiation, wind speed, and barometric pressure. A total of 99 sensors were placed over the winters 2010/2011 and 2011/2012 at multiple locations within three 40–180 km2 basins in the Black Forest region of Southern Germany. The locations were chosen to cover a wide range of slopes, elevations, and expositions in a stratified sampling design. Furthermore, “paired stations” located in close proximity to each other, one in the open and one underneath various forest canopies, were set up to investigate the influence of vegetation on snow dynamics. The results showed that considerable differences in snow depth and, therefore, snow water equivalent (SWE) are present within the study area despite its moderate temperatures and medium elevation range (400–1500 m). The relative impact of topographical factors like elevation, aspect, and of different types of forest vegetation were quantified continuously and were found to change considerably over the winter period. The recorded differences in SWE and snow cover duration were large enough that they should be considered in hydrologic and climate models.

A New Low-Cost, Stand-Alone Sensor System for Snow Monitoring

Abstract Monitoring continuous changes in snowpack dynamics and its meteorological drivers is critical for understanding key aspects of water resources, climate variability, and ecology. While manual snow surveys have traditionally been used to evaluate snow processes, their high costs and discrete measurements can lead to biased estimations of accumulation and ablation rates. Ultrasonic range sensors offer an alternative to continuously monitor snow depth but their widespread employment has been limited because of high prices. This paper describes the development of an inexpensive prototype ultrasonic sensor suite characterized by a ready-to-use stand-alone design and flexibility to incorporate additional meteorological instruments. The performance of 48 units was tested during a winter season in central British Columbia, recording snow depth and air temperature data consistent with those from nearby weather stations and manual measurements. Despite a relatively small underestimation of snow depth due to...

Near-optimal mobile robot recharging with the rate-maximizing forager

We examine the practical problem of a mobile autonomous robot performing a long-duration survey task, during which it must recharge its batteries periodically. We present a scalable, online, heuristic method that allows the robot to recharge efficiently, thus maximizing its rate of work. The method is a direct application of the rate-maximizing foraging model, which seeks to explain the behaviour of animals solving related problems. Simulation results suggest that the method performs very well compared to optimal and naive heuristic approaches.

Feature-rich path planning for robust navigation of MAVs with Mono-SLAM

We present a path planning method for MAVs with vision-only MonoSLAM that generates safe paths to a goal according to the information richness of the environment. The planner runs on top of monocular SLAM and uses the available information about structure of the environment and features visibility to find trajectories that maintain visual contact with feature-rich areas. The MAV continuously re-plans as it explores and updates the feature-points in the map. In real-world experiments we show that our system is able to avoid paths that lead into visually-poor sections of the environment by considering the distribution of visual features. If the same system ignores the availability of visually-informative regions in the planning, it is unable to estimate its state accurately and fails to reach its goal.

BearCam: automated wildlife monitoring at the arctic circle

In this paper we describe the development of the BearCam, a camera system which was deployed in Fall 2005 to monitor the behaviour of grizzly bears at a remote location near the arctic circle. The system aided biologists in collecting the data for their study on bears’ behavioural responses to ecotourists. We developed a camera system for operating in the challenging arctic conditions. We describe a novel “motion shapelet” algorithm for automatically detecting bears in the video captured by this camera system. This algorithm is an extension of the shapelet features (Sabzmeydani and Mori in CVPR 2007), which are mid-level features capturing pieces of shape. Our extension of this technique incorporates motion information and proves effective at automatically detecting the occurrence of bears. We present quantitative results demonstrating that our algorithm can reliably detect bears in the vast amounts of video footage collected by our system.

Robot task switching under diminishing returns

We investigate the problem of a robot maximizing its long-term average rate of return on work. We present a means to obtain an estimate of the instantaneous rate of return when work is rewarded in discrete atoms, and a method that uses this to recursively maximize the long-term average return when work is available in localized patches, each with locally diminishing returns. We examine a puck-foraging scenario, and test our method in simulation under a variety of conditions. However, the analysis and approach applies to the general case.

A robust integrated system for selecting and commanding multiple mobile robots

We describe a system whereby multiple humans and mobile robots interact robustly using a combination of sensing and signalling modalities. Extending our previous work on selecting an individual robot from a population by face-engagement, we show that reaching toward a robot - a specialization of pointing - can be used to designate a particular robot for subsequent one-on-one interaction. To achieve robust operation despite frequent sensing problems, the robots use three phases of human detection and tracking, and emit audio cues to solicit interaction and guide the behaviour of the human. A series of real-world trials demonstrates the practicality of our approach.

UAV, do you see me? Establishing mutual attention between an uninstrumented human and an outdoor UAV in flight

We present the first demonstration of establishing mutual attention between an outdoor UAV in autonomous normal flight and an uninstrumented human user. We use the familiar periodic waving gesture as a signal to attract the UAVs attention. The UAV can discriminate this gesture from human walking and running that appears similarly periodic. Once a signaling person is observed and tracked, the UAV acknowledges that the user has its attention by hovering and performing a “wobble” behavior. Both parties are now ready for further interaction. The system works on-board the UAV using a single camera for input and is demonstrated working reliably in real-robot trials.