We present the design and implementation of a small autonomous unmanned aerial vehicle capable of high-speed flight through complex natural environments. Using only onboard GPS-denied sensing and computation, we perform obstacle detection, planning, and feedback control in realtime. We present a novel integrated approach to perception and control using pushbroom stereo, which exploits forward m...

We develop a vision system for highly mobile autonomous agents that is capable of dynamic obstacle avoidance and active perception. We demonstrate the robust performance of the system in artificial animals with directable, foveated eyes, situated in physics-based virtual worlds. Through active perception, each agent controls its eyes and body by continuously analyzing photorealistic binocular r...

Currently the research on the map visualization and GIS visualization is relatively mature. But in the indoor environment, Indoor positioning system requires monitoring the location which is on vector map of positioning data and display positioning data trajectory. At the same time, Indoor positioning environment is complex, and has many obstacles such as walls. The connection between two posit...

On account of the complex application environment and the large number of uncertain conditions for the palletizing robot, we do path-planning for the multiple joints robot by the algorithm based on Hierarchical Markov Decision Process. First, according to the actual working environment, we set the range of the robot’s motion and select the conventional movement combination as the basic set of t...

A teleoperation system has been developed that enables two human operators to safely control two collaborative mobile robots in unknown and dynamic environments from any two PCs connected to the Internet by installing developed client program on them and by using simple force feedback joysticks. On the graphical user interfaces, the operators receive images forwarded by the cameras mounted on t...

This paper introduces MOANTOOL a Matlab-based toolbox for formulating, solving, and simulating model predictive controllers (MPC) with embedded obstacle avoidance functionality. The toolbox offers a simple, yet powerful user interface that allows control researchers and practitioners to set up even complex control problems with just a few lines of code. MOANTOOL fully automates tedious mathemat...

Future Naval operations necessitate the incorporation of autonomous underwater vehicles into a collaborative network. In future complex missions, a forward look capability will also be required to map and avoid obstacles such as sunken ships and reefs. Following previous work on steering control, this work examines collision avoidance behaviors in bottom following using a hypothetical forward-l...

In this paper, we present our approach to solve a physics-based reinforcement learning challenge “Learning to Run” with objective to train physiologically-based human model to navigate a complex obstacle course as quickly as possible. The environment is computationally expensive, has a highdimensional continuous action space and is stochastic. We benchmark state of the art policy-gradient metho...

Granular flows are a complex process, involving wide range of grain sizes, materials, varied viscous fluids, among others. For this reason, the simulation granular requires certain level simplification, allowing isolated study its governing variables and extending global observations to field events. Here, we present planar setup as an alternative for studying simplified processes associated fl...

OBJECTIVE Patients with rheumatoid arthritis (RA) are at increased risk of falling. In healthy elderly persons with a history of falling, a reduced ability to avoid obstacles while walking has been shown to relate to increased fall risk. The aim of this study was to determine whether this potential risk factor for falls would also be present in persons with RA. METHODS Twelve RA patients and ...