18 research outputs found
Autonomous Robots in Dynamic Indoor Environments: Localization and Person-Following
No full textAutonomous social robots have many tasks that they need to address such as localization, mapping, navigation, person following, place recognition, etc. In this thesis we focus on two key components required for the navigation of autonomous robots namely, person following behaviour and localization in dynamic human environments. We propose three novel approaches to address these components; two approaches for person following and one for indoor localization. A convolutional neural networks based approach and an Ada-boost based approach are developed for person following. We demonstrate the results by showing the tracking accuracy over time for this behaviour. For the localization task, we propose a novel approach which can act as a wrapper for traditional visual odometry based approaches to improve the localization accuracy in dynamic human environments. We evaluate this approach by showing how the performance varies with increasing number of dynamic agents present in the scene. This thesis provides qualitative and quantitative evaluations for each of the approaches proposed and show that we perform better than the current approaches
Indoor Localization in Dynamic Human Environments Using Visual Odometry and Global Pose Refinement
No full textLearning Vector-space Representations of Items for Recommendations Using Word Embedding Models
No full textAbstractWe present a method of generating item recommendations by learning item feature vector embeddings. Our work is analogous to approaches like Word2Vec or Glove used to generate a good vector representation of words in a natural language corpus. We treat the items that a user interacted with as analogous to words and the string of items interacted with in a session as sentences. Our embedding generates semantically related clusters and the item vectors generated can be used to compute item similarity which can be used to drive product recommendations. Our method also allows us to use the feature vectors in other machine learning systems. We validate our method on the MovieLens dataset
MRPT/mrpt: Release of v2.11.7
No full text<h1>Version 2.11.7: Released Jan 25th, 2024</h1>
<ul>
<li>Changes in apps:<ul>
<li>carmen2rawlog: Generate valid timestamps.</li>
</ul>
</li>
<li>Changes in libraries:<ul>
<li>rosbag2rawlog: Add support for <code>sensor_msgs/CompressedImage</code> topics.</li>
</ul>
</li>
<li>BUG FIXES:<ul>
<li>mrpt::hwdrivers::CImageGrabber_dc1394 did not mark the right image as present in stereo cameras.</li>
<li>kinect-stereo-calib: Fix exception un-distorting images.</li>
</ul>
</li>
</ul>
MRPT/mrpt: Release of v2.13.0
No full text<h1>Version 2.13.0: Released May 19th, 2024</h1>
<ul>
<li>Changes in apps:<ul>
<li>SceneViewer3D: it now automatically guesses the min/max clip planes from the scene bounding box.</li>
<li>rosbag2rawlog (ROS1): tolerate loss of some sensor observations if /tf has not been yet received instead of aborting conversion.</li>
</ul>
</li>
<li>Changes in libraries:<ul>
<li>\ref mrpt_containers_grp:<ul>
<li>New methods returning safe proxy objects for range-based for loops:<ul>
<li>mrpt::containers::yaml::asMapRange()</li>
<li>mrpt::containers::yaml::asSequenceRange()</li>
</ul>
</li>
<li>Upgrade embedded simpleini to v4.22 (for use when not found in the system)</li>
</ul>
</li>
<li>\ref mrpt_hwdrivers_grp<ul>
<li>mrpt::hwdrivers::CJoystick API updated so it can handle an arbitrary number of axes.</li>
</ul>
</li>
<li>\ref mrpt_maps_grp<ul>
<li>mrpt::maps::CVoxelMap and mrpt::maps::CVoxelMapRGB: Added insertion option <code>remove_voxels_farther_than</code>.</li>
<li>Removed unused method: mrpt::maps::COccupancyGridMap2D::saveAsEMFTwoMapsWithCorrespondences()</li>
</ul>
</li>
<li>Removed seldom used code (if needed, refer to MRPT versions <2.13.0):<ul>
<li>The whole module mrpt-detectors</li>
<li>mrpt::hwdrivers::CBoardENoses</li>
<li>mrpt::hwdrivers::CBoardSonars</li>
<li>mrpt::hwdrivers::CDUO3DCamera</li>
<li>mrpt::hwdrivers::CPtuDPerception</li>
<li>mrpt::hwdrivers::CRoboticHeadInterface</li>
<li>mrpt::hwdrivers::CTuMicos</li>
</ul>
</li>
</ul>
</li>
<li>BUG FIXES:<ul>
<li>mrpt::hwdrivers::CJoystick: Crash due to missing #include of OS-specific configuration in CJoystick.h</li>
<li>mrpt::expr::CRuntimeCompiledExpression::is_compiled() did always return <code>true</code>.</li>
</ul>
</li>
</ul>
