Offroad Navigation Using Adaptable Motion Patterns

Abstract

We present a navigation system which is able to steer an electronically controlled ground vehicle to given destinations considering all obstacles in its vicinity. The approach is designed for vehicles without a velocity controlled drive-train, making it especially useful for typical remotecontrolled vehicles. The vehicle is controlled by sets of commands, each set representing a specific maneuver. These sets are combined in a tree-building procedure to form trajectories towards the given destination. While the sets of commands are executed the vehicle's behavior is measured to refine the prediction used for path generation. This enables the approach to adapt to surface alterations. We tested our system using a 400 kg EOD robot in an outdoor environment.

Collective motion pattern scaling for improved open-loop off-road navigation

“…This technique was combined with an exponential smoothing (see below) to form the first version of the learning Motion Pattern based local navigation. The potential of this basic system has been shown in [5]. Both learning approaches, the basic version from [5] and the improved version discussed here, as well as the planning mechanism assume, that applied Motion Patterns yield in similar trajectories repeatedly.…”

“…The potential of this basic system has been shown in [5]. Both learning approaches, the basic version from [5] and the improved version discussed here, as well as the planning mechanism assume, that applied Motion Patterns yield in similar trajectories repeatedly. The exponential smoothing can cope with singular discontinuities, but it is not able to handle continuously changing results, i.e.…”

“…A planning tree of collision free paths that has been build using Motion Patterns in an 2-dimensional simulated environment. an occupancy grid [5]. The corresponding sequence of series of commands C P = (U 1 , .…”

“…Based on the model above, we can now also build a collision-free tree of Motion Patterns and extract the best path towards the destination. The path planning process is described in detail in [5] and an example tree generated by this technique can be seen in Fig. 2.…”

Unmanned multi-robot CBRNE reconnaissance with mobile manipulation System description and technical validation

“…Regrettably, a full description of this approach is beyond the scope of this paper. An overview with respect to this CBRNE project is given in [9], all details can be found in [10].…”