Robot navigation over large areas inevitably has to rely on maps of the environment. The standard manner in which such maps are defined is through geometry, e.g. through traversability grid maps or through a division of the environment into free-space and obstacle-space. In this paper, we combine certain aspects of the geometric maps, through the notion of distinctive places, with a topological...

In this paper, we have described a technique for terrain traversability assessment modeling of mobile robots operating in natural terrain and presented a fast near-optimum algorithm for autonomous navigational path planning of mobile robots in rough terrain environments. The proposed method is based on visual sensing of terrain salient features and analysis of geo-location coordinates of the sa...

We are developing techniques for safeguarding the remote operation of lunar rovers. This paper presents two complementary techniques: One, based on stereo vision, evaluates the traversability of paths the rover could follow, and produces preferences for steering directions. The other, based on laser proximity sensing, looks for hazards immediately in front of the rover, commanding an emergency ...

A large-scale navigation system for autonomous off-road robots is presented which uses a topological map to navigate to a previously unseen target location. During path traversal, the system relies on a local navigation layer to avoid obstacles not modeled in the map. Data from this local layer is abstracted to learn both realistic topological edge cost measures and local traversability maps wh...

In this paper, we develop Fringe-Saving A* (FSA*), an incremental version of A* that repeatedly finds shortest paths in a known gridworld from a given start cell to a given goal cell while the traversability costs of cells increase or decrease. The first search of FSA* is the same as that of A*. However, FSA* is able to find shortest paths during the subsequent searches faster than A* because i...

In this paper, an obstacle detection system for field applications is presented which relies on the output of a stereo vision camera. In a first step, it splits the point cloud into cells which are analyzed in parallel. Here, features like density and distribution of the points and the normal of a fitted plane are taken into account. Finally, a neighborhood analysis clusters the obstacles and i...

In this paper, recent progress in the development of the DLR Crawler a six-legged, actively compliant walking robot prototype is presented. The robot implements a walking layer with a simple tripod and a more complex biologically inspired gait. Using a variety of proprioceptive sensors, different reflexes for reactively crossing obstacles within the walking height are realised. On top of the wa...

Teaching a robot to perceive and navigate in an unstructured natural world is a difficult task. Without learning, navigation systems are short-range and extremely limited. With learning, the robot can be taught to classify terrain at longer distances, but these classifiers can be fragile as well, leading to extremely conservative planning. A robust, high-level learning-based perception system f...

In recent years, the numbers of life-size humanoids as well as their mobile capabilities have steadily grown. Stable walking motion and control for humanoid robots are active fields of research. In this scenario an open question is how to model and analyse the scene so that a motion planning algorithm can generate an appropriate walking pattern. This paper presents the current work towards scen...

We consider the problem of optimal control design for navigation on off-road terrain. use a traversability measure to characterize difficulty The captures terrain properties essential navigation, such as elevation maps, roughness, slope, and texture. with presence or absence obstacles becomes particular case proposed measure. provide convex formulation by lifting density space using linear Perr...