Gautam Narang

Autonomous robot navigation using Simultaneous localization and mapping (SLAM) is essential for scene under- standing by robots. Most existing systems use visual information, and even though such visual-based technologies are robust and useful for many situations, they have difficulty dealing with certain scenarios such as occluded goal or when the goal is out of frame. Introducing audio information to the navigation system solves these issues effectively. Several audio-based methods have been… Show more

Autonomous robot navigation using Simultaneous localization and mapping (SLAM) is essential for scene under- standing by robots. Most existing systems use visual information, and even though such visual-based technologies are robust and useful for many situations, they have difficulty dealing with certain scenarios such as occluded goal or when the goal is out of frame. Introducing audio information to the navigation system solves these issues effectively. Several audio-based methods have been developed in the past to deal with these issues. However, these existing audio-based methods have been developed with the assumption that the space around the robot is open i.e. no sound reflection occurs. Hence, the invisible goals where the sound reflection can be localized have not been fully considered. This paper proposes a reflection-robust sound source localization method using visual SLAM. This method can deal with sound sources whose direct paths are not available, and using localiza- tion, we can set a goal only for the actual sound source. Also, to correct the drift present in the local estimates of Visual Odometry (VO), SLAM was integrated with the system, thus increasing the accuracy and robustness of mapping and navigation of our proposed method. The performance of the proposed system is compared to conventional methods, and it proves to be very efficient and robust especially in extremely reverberant situations. It was found that the integration of VO and SLAM improved the average error of a map by approximately 50 pts, and the accuracy of SSL for direct path of sounds was improved by approximately 8 pts. With the online implementation of these methods we successfully achieved audio visual navigation for the actual sound sources. Show less

WABIAN-2R is a bipedal humanoid robot which is capable of stretched knee walking with heel-contact and toe-off motions due to the presence of a 2-DoF waist and a passive joint for bending toe motion, and can thus mimic human-like walking. This paper aims to determine the similarity between the walking gait of WABIAN-2R to the natural walking gait of a human of comparable size and stature, on the factors (i) pelvic tilt, (ii) pelvic rotation, (iii) swing and stance percentage, and (iv) double… Show more

WABIAN-2R is a bipedal humanoid robot which is capable of stretched knee walking with heel-contact and toe-off motions due to the presence of a 2-DoF waist and a passive joint for bending toe motion, and can thus mimic human-like walking. This paper aims to determine the similarity between the walking gait of WABIAN-2R to the natural walking gait of a human of comparable size and stature, on the factors (i) pelvic tilt, (ii) pelvic rotation, (iii) swing and stance percentage, and (iv) double limb support and single limb support percentage using inertial measurement units and force-torque sensors. Show less

Stroke is one of the leading causes of long-term disability worldwide. Present techniques employed for rehabilitation of victims suffering from partial paralysis or loss of function, such as mirror therapy, require substantial amount of resources, which may not be readily available. In traditional mirror therapy, patients place a mirror beside the functional limb, blocking their view of the affected limb, creating the illusion that both the limbs are working properly, which enhances recovery by… Show more

Stroke is one of the leading causes of long-term disability worldwide. Present techniques employed for rehabilitation of victims suffering from partial paralysis or loss of function, such as mirror therapy, require substantial amount of resources, which may not be readily available. In traditional mirror therapy, patients place a mirror beside the functional limb, blocking their view of the affected limb, creating the illusion that both the limbs are working properly, which enhances recovery by enlisting direct simulation. This paper proposes an alternate robot based concept, named Wear-A-BAN, where the rehabilitative task will be carried out by a normal articulated industrial robot. During the proposed rehabilitative procedure, the patients are made to wear a smart sleeve on the functional limb. Movement of this limb is monitored in real-time, by wireless Body-Area Network (BAN) sensors placed inside the sleeve, and copied over the sagittal plane to the affected limb. This procedure results in considerable savings in terms of money and personnel, as even though this procedure does not make the rehabilitation process autonomous, but one therapist can monitor various patients at a time. The industrial robot used is suitable for this purpose due to safety aspects naturally existing in the robot, is relatively cheap in price, and allows comprehensive 3-D motions of the limb. Also, unlike traditional therapy, this procedure allows actual movement of the affected limb. The sensors can also be used for other applications, such as gaming and daily life personal activity monitoring. Show less