Localization of mobile robots can be challenging in highly dynamic environments (airport terminals, stores, hospitals) yet these areas offer great potential for robotics applications. HighWiFi coverage provides a way to localize even low-cost robots that do not need to be equipped with expensive exteroceptive sensors or excessive computational power to run visual-based SLAM algorithms. Since current trend in robotics is in mass-deployment of low-cost, replaceable robots, we focus our efforts in this direction as well. Possible solution is combination of high-tech robots deployed as support assuring reliable localization for the low-cost robots that are actually doing the job. The proposed scenario is to use one SLAM robot to map WiFi signal strength in the working area and provide it to a low-cost robot to correct drift of its 6-DOF gyro-odometry localization system. For this purpose, we extend Gaussian-processes-based WiFi localization algorithms to full 3D and experimentally evaluate the proposed approach in 2 mapping and 7 localization sorties performed on different dates spanning four months.

Controlling mobile robots with complex articulated parts and hence many degrees of freedom generates high cognitive load on the operator, especially under demanding conditions such as in Urban Search & Rescue missions. We propose a solution based on reinforcement learning in order to accommodate the robot morphology automatically to the terrain and the obstacles it traverses. In this paper, we concentrate on the crucial issue of predicting rewards from incomplete or missing data. For this purpose we exploit the Gaussian processes as a predictor combined with decision trees. We demonstrate our achievements in a series of experiments on real data.

In this paper we introduce the concept of Adaptive Traversability (AT), which we define as means of autonomous motion control adapting the robot morphology - configuration of articulated parts and their compliance - to traverse unknown complex terrain with obstacles in an optimal way. We verify this concept by proposing a reinforcement learning based AT algorithm for mobile robots operating in such conditions. We demonstrate the functionality by training the AT algorithm under lab conditions on simple EUR-pallet obstacles and then testing it successfully on natural obstacles in a forest. For quantitative evaluation we define a metrics based on comparison with expert operator. Exploiting the proposed AT algorithm significantly decreases the cognitive load of the operator.

This paper proposes a novel approach to improving precision and reliability of odometry of skid-steer mobile robots by means inspired by robotic terrain classification (RTC). In contrary to standard RTC approaches we do not provide human labeled discrete terrain categories but we classify the terrain directly by the values of coefficients correcting the robot's odometry. Hence these coefficients make the odometry model adaptable to the terrain type due to inherent slip compensation. Estimation of these correction coefficients is based on feature extraction from the vibration data measured by an inertial measurement unit and regression function trained offline. Statistical features from the time domain, frequency domain, and wavelet features were explored and the best were automatically selected. To provide ground truth trajectory for the purpose of offline training a portable overhead camera tracking system was developed. Experimental evaluation on rough outdoor terrain proved 67.9±7.5% improvement in RMSE in position with respect to a state of the art odometry model. Moreover, our proposed approach is straightforward, easy for online implementation, and low on computational demands.

It is an important ability for any mobile robot to be able to estimate its posture and to gauge the distance it traveled. In this paper, we have addressed this problem in a dynamic quadruped robot by combining traditional state estimation methods with machine learning. We have designed and implemented a navigation algorithm for full body state (position, velocity, and attitude) estimation that uses no external reference but relies on multimodal proprioceptive sensory information only. The extended Kalman filter (EKF) was used to provide error estimation and data fusion from two independent sources of information: 1) strapdown mechanization algorithm processing raw inertial data and 2) legged odometry. We have devised a novel legged odometer that combines information from a multimodal combination of sensors (joint and pressure). We have shown our method to work for a dynamic turning gait, and we have also successfully demonstrated how it generalizes to different velocities and terrains. Furthermore, our solution proved to be immune to substantial slippage of the robot's feet.

Precise and reliable estimation of orientation plays crucial role for any mobile robot operating in unknown environment. The most common solution to determination of the three orientation angles: pitch, roll, and yaw, relies on the Attitude and Heading Reference System (AHRS) that exploits inertial data fusion (accelerations and angular rates) with magnetic measurements. However, in real world applications strong vibration and disturbances in magnetic field usually cause this approach to provide poor results. Therefore, we have devised a new approach to orientation estimation using inertial sensors only. It is based on modified complementary filtering and was proved by precise laboratory testing using rotational tilt platform as well as by robot field-testing. In the final, the algorithm well outperformed the commercial AHRS solution based on magnetometer aiding.

It is an important ability for any mobile robot to be able to estimate its posture and to gauge the distance it travelled. The information can be obtained from various sources. In this work, we have addressed this problem in a dynamic quadruped robot. We have designed and implemented a navigation algorithm for full body state (position, velocity, and attitude) estimation that does not use any external reference (such as GPS, or visual landmarks). Extended Kalman Filter was used to provide error estimation and data fusion from two independent sources of information: Inertial Navigation System mechanization algorithm processing raw inertial data, and legged odometry, which provided velocity aiding. We present a novel data-driven architecture for legged odometry that relies on a combination of joint sensor signals and pressure sensors. Our navigation system ensures precise tracking of a running robot's posture (roll and pitch), and satisfactory tracking of its position over medium time intervals. We have shown our method to work for two different dynamic turning gaits and on two terrains with significantly different friction. We have also successfully demonstrated how our method generalizes to different velocities.