Figure 1 - uploaded by Olac Luis Fuentes
Content may be subject to copyright.
Source publication
We present an approach for autonomous learning of dextrous manipulation skills. We use heuristics derived from observations made on human hands to reduce the degrees of freedom of the task and make learning tractable. Our approach consists of learning and storing a few basis manipulation primitives for a few prototypical objects and then using a ne...
Context in source publication
Context 1
... Learning to Manipulate Objects Figure 1 shows the general structure of our manipulation system, including its learning component. The input is a perceptual goal and the output is a robot command that when executed by the robot will take it to a connguration that will satisfy the goal. ...
Similar publications
Informed by twenty years of hands-on experimentation with autonomous and robotic systems in home prototypes at [REDACTED], this study provides insight into the motivations and values of integrating computing technologies in residential architecture. Although optimising home adaptability for energy efficiency, ergonomics, and climate control is show...
This paper describes a robotics based surveillance system for indoors operation. The system is capable of performing common tasks autonomously such as detect-ing an intruder and having a robot approaching it while the rest of the team spreads to maximize the coverage of the area. The system developed is a small size networked sys-tem with fixed cam...
![Figure 1. SHRIMP robot design [3] Figure 2. Robot chassis with flexible...](profile/Handry-Khoswanto/publication/270701811/figure/fig1/AS:669971222900746@1536744995426/SHRIMP-robot-design-3-Figure-2-Robot-chassis-with-flexible-shape_Q320.jpg)
Robot application in disaster area can help responder team to save victims. In order to finish task, robot must have flexible movement mechanism so it can pass through uncluttered area. Passive linkage can be used on robot chassis so it can give robot flexibility. On physical experiments, robot is succeeded to move through gravels and 5 cm obstacle...
This paper presents an intelligent autonomous document mobile delivery robot using a deep learning approach. The robot is built as a prototype for document delivery service for use in offices in which it can adaptively move across different surfaces, such as terrazzo, canvas, and wooden. In this work, we introduce a convolutional neural network (CN...
Regular inspection is indispensable during the operation period of existing buildings.
However, the current approaches involve a high number of manual operations and are by large limited to the inspection of visible elements. Autonomous wall-climbing robot with through-wall imaging module to perform visual inspection of concealed components has the...
