31,078 Hits in 4.4 sec

Improving Robot Success Detection using Static Object Data [article]

Rosario Scalise, Jesse Thomason, Yonatan Bisk, Siddhartha Srinivasa
2019 arXiv   pre-print
We use static object data to improve success detection for stacking objects on and nesting objects in one another.  ...  We show that adding static data about the objects themselves improves the performance of an end-to-end pipeline for classifying action outcomes.  ...  Contributions: • We show that vision and language data about objects improves detection success for robot action outcomes; • we provide an end-to-end model for detecting successful placement of one object  ... 
arXiv:1904.01650v2 fatcat:tzvqfp4xhfcgdcxkut2mz2dtwm

Improving indoor navigation of autonomous robots by an explicit representation of doors

Matthias Nieuwenhuisen, Jörg Stückler, Sven Behnke
2010 2010 IEEE International Conference on Robotics and Automation  
Also, mobile manipulation capabilities can only be utilized, if the robot knows about the movability of objects.  ...  During localization, the state of doors is estimated from measurements while it is simultaneously used to improve localization robustness and accuracy.  ...  [4] detect objects that moved between scans of the environment. They describe the shape of detected objects as local grid maps and use these to recognize objects in future scans.  ... 
doi:10.1109/robot.2010.5509689 dblp:conf/icra/NieuwenhuisenSB10 fatcat:vvx4hdbj7ndtbgta5wa6zmseg4

Under Pressure: Learning to Detect Slip with Barometric Tactile Sensors [article]

Abhinav Grover, Christopher Grebe, Philippe Nadeau, Jonathan Kelly
2021 arXiv   pre-print
Further, we test our detector on two robot manipulation tasks involving common household objects and demonstrate successful generalization to real-world scenarios not seen during training.  ...  Part of the challenge lies in identifying slip and other key events from the tactile data stream. In this paper, we present a learning-based method to detect slip using barometric tactile sensors.  ...  In a given trial, each object was tapped on the top and on its side; the trial was deemed successful if slip was registered when the object was tapped and the detector output returned to the nominal (static  ... 
arXiv:2103.13460v4 fatcat:difruaxepjc6tlmaqwekubf4li

Human-Robot Motion Control Application with Artificial Intelligence for a Cooperating YuMi Robot

Roman Michalík, Aleš Janota, Michal Gregor, Marián Hruboš
2021 Electronics  
The program can be expanded by integrating other IoT devices to help control the robot and collect data useful for a needed application.  ...  The use of sensors on gloves or other controls to control robots may restrict both operation of the robot and the operator's activities.  ...  Success in our case means successfulness of detection of the desired number of outstretched fingers.  ... 
doi:10.3390/electronics10161976 fatcat:mqss6fllajfzrgrqsb6h3sekhq

Fast Perception, Planning, and Execution for a Robotic Butler: Wheeled Humanoid M-Hubo [article]

Moonyoung Lee, Yujin Heo, Jinyong Park, Hyun-Dae Yang Ho-Deok Jang, Philipp Benz, Hyunsub Park, In So Kweon, Jun-Ho Oh
2020 arXiv   pre-print
To address this issue, we propose a unique strategy of integrating a 3D object detection pipeline with a kinematically optimal manipulation planner to significantly increase speed performance at runtime  ...  In addition, we develop a new robotic butler system for a wheeled humanoid that is capable of fetching requested objects at 24% of the speed a human needs to fulfill the same task.  ...  Fig. 8 : 8 Estimated localization and ground truth data as robot moves throughout static indoor room.  ... 
arXiv:2001.00356v1 fatcat:xqn4hr4hr5h2rg3oucnv3vo5su

Physically-based grasp quality evaluation under uncertainty

Junggon Kim, Kunihiro Iwamoto, James J. Kuffner, Yasuhiro Ota, Nancy S. Pollard
2012 2012 IEEE International Conference on Robotics and Automation  
The effectiveness of the new quality measures on predicting the actual grasp success rate is shown through a real robot experiment.  ...  In this paper new grasp quality measures considering both object dynamics and pose uncertainty are proposed.  ...  They combined the data from a set of object detection algorithms using a probabilistic framework to find an optimal grasp.  ... 
doi:10.1109/icra.2012.6225342 dblp:conf/icra/KimIKOP12 fatcat:ymfyqzumc5am7alo2fmjmt56ji

A novel navigation scheme in dynamic environment using layered costmap

Xiaoning Han, Yuquan Leng, Haitao Luo, Weijia Zhou
2017 2017 29th Chinese Control And Decision Conference (CCDC)  
Fig 1 The "wall" formed by person trajectory when treated as a static object 7123 978-1-5090-4657-7/17/$31.00 c 2017 IEEE  ...  Navigation is one of basic functions of auto-mobile robots. After dozens of years of development, now the navigation in static environment almost has been realized, taking the method in ROS (i.e.  ...  Using the concept of "encounter time", we converse the dynamic objects as virtual static ones, thus the previous static-environment based path-planning can be used.  ... 
doi:10.1109/ccdc.2017.7978468 fatcat:dm5h4vwf25bbjnw2gwpxmttxtu

Slip Detection With a Biomimetic Tactile Sensor

Jasper Wollaston James, Nicholas Pestell, Nathan F. Lepora
2018 IEEE Robotics and Automation Letters  
Slip detection helps to prevent robotic hands from dropping grasped objects and would thus enable complex object manipulation.  ...  Performance of the slip detection method is then validated under several test conditions, including varying the speed at which slip onset occurs and using novel shaped objects.  ...  The data used can be accessed at  ... 
doi:10.1109/lra.2018.2852797 dblp:journals/ral/JamesPL18 fatcat:5rqqyic6xjgwhkabeta2ez6s3m

Multiple-model RANSAC for ego-motion estimation in highly dynamic environments

Shao-Wen Yang, Chieh-Chih Wang
2009 2009 IEEE International Conference on Robotics and Automation  
To accommodate RANSAC to multiple models -a static environment model for ego-motion estimation and a moving object model for moving object detection, a compact representation models moving object information  ...  and the motion of the robot itself.  ...  A stationary object map and a moving object map are accumulated and used for moving object detection. Zhao et al.  ... 
doi:10.1109/robot.2009.5152239 dblp:conf/icra/YangW09 fatcat:bhhwwoz3gbfkbcs7fnn6yinhni

Navigation toward Non-static Target Object Using Footprint Detection Based Tracking [chapter]

Meng Yi, Yinfei Yang, Wenjing Qi, Yu Zhou, Yunfeng Li, Zygmunt Pizlo, Longin Jan Latecki
2013 Lecture Notes in Computer Science  
The destination of a traditional robot navigation task is usually a static location.  ...  A Footprint Detection based Tracker (FD-Tracker) is proposed to robustly track the target object in such scenarios.  ...  These approaches set the navigation goal to be a static location, but our robot understands the notion of object and can navigate to a non-static target.  ... 
doi:10.1007/978-3-642-37431-9_30 fatcat:lzcryjnj5vhojlu2wicmtvpwt4

Issues and experimental results in vision‐guided robotic grasping of static or moving objects

Nikolaos Papanikolopoulos, Christopher E. Smith
1998 Industrial robot  
Using a vision system for grasping of static or moving objects presents several issues with respect to sensing, control, and system configuration.  ...  of grasping objects.  ...  The second set demonstrates that the improved version meets our target success rate for static grasping, while still suggesting improvements that might be made to the system.  ... 
doi:10.1108/01439919810204748 fatcat:v5qurib3xfcv5ay6n4fwv35q54

Design and VLSI Implementation of Anticollision Enabled Robot Processor Using RFID Technology

Joyashree Bag
2012 International Journal of VLSI Design & Communication Systems  
In multi-robot environment, when many robots are moving in the same workspace, there is a possibility of their physical collision with themselves as well as with physical objects.  ...  It can be employed for robot navigation.  ...  The processor of the robot will process some steps for successful collision avoidance operation with static as well as dynamic objects. Each robot has one RFID tag and processor attached with it.  ... 
doi:10.5121/vlsic.2012.3605 fatcat:3ha3xa6gwbbpzbltbc7i2m5k5a

A mobile robot visual SLAM system with enhanced semantics segmentation

Feng Li, Weijun Li, Wenfeng Chen, Weifeng Xu, Lingqing Huang, Dan Li, Shuting Cai, Ming Yang, Xiaoming Xiong, Yuan Liu
2020 IEEE Access  
In this paper, we develop a more efficient semantic SLAM system in the two-wheeled mobile robot by using semantic segmentation to recognize people, chairs, and other objects in every keyframe.  ...  Besides, for the incomplete identification of movable objects, we used image processing algorithms to enhance the semantic segmentation effect.  ...  Our system enables mobile robots to recognize and distinguish dynamic objects and static objects in the scene by using encoder data and image data.  ... 
doi:10.1109/access.2020.2970238 fatcat:5ab2onw22zgprhhbqpummpc2by

Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter [article]

Douglas Morrison, Peter Corke, Jürgen Leitner
2019 arXiv   pre-print
Where other approaches use a static camera position or fixed data collection routines, our Multi-View Picking (MVP) controller uses an active perception approach to choose informative viewpoints based  ...  In trials of grasping 20 objects from clutter, our MVP controller achieves 80% grasp success, outperforming a single-viewpoint grasp detector by 12%.  ...  from two static cameras.  ... 
arXiv:1809.08564v2 fatcat:cr4j6autjrggvfjpwt6zsdbnr4

Unsupervised and online non-stationary obstacle discovery and modeling using a laser range finder

G. Duceux, D. Filliat
2014 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We propose an approach that makes it possible to detect, learn and recognize these objects through a multi-view model, using only a planar laser range finder.  ...  However, most of existing methods assume a mostly static world and filter away dynamic aspects while those dynamic aspects are often caused by non-stationary objects which may be important for the robot  ...  The use of descriptors instead of raw range data also improves robustness to noise.  ... 
doi:10.1109/iros.2014.6942620 dblp:conf/iros/DuceuxF14 fatcat:emxipvrczzch5e3o3bakyai4se
« Previous Showing results 1 — 15 out of 31,078 results