Visual Based Localization for a Legged Robot
نویسندگان
چکیده
This paper presents a visual based localization mechanism for a legged robot in indoor office environments. Our proposal is a probabilistic approach which uses partially observable Markov decision processes. We use a precompiled topological map where natural landmarks like doors or ceiling lights are recognized by the robot using its on-board camera. Experiments have been conducted using the AIBO Sony robotic dog showing that it is able to deal with noisy sensors like vision and to approximate world models representing indoor office environments. The major contributions of this work is the use of an active vision as the main input and localization in not-engineered environments.
منابع مشابه
Energy Dissipation Rate Control Via a Semi-Analytical Pattern Generation Approach for Planar Three-Legged Galloping Robot based on the Property of Passive Dynamic Walking
In this paper an Energy Dissipation Rate Control (EDRC) method is introduced, which could provide stable walking or running gaits for legged robots. This method is realized by developing a semi-analytical pattern generation approach for a robot during each Single Support Phase (SSP). As yet, several control methods based on passive dynamic walking have been proposed by researchers to provide an...
متن کاملExpectation-Based Vision for Self-Localization on a Legged Robot
This paper presents and empirically compares solutions to the problem of vision and self-localization on a legged robot. Specifically, given a series of visual images produced by a camera on-board the robot, how can the robot effectively use those images to determine its location over time? Legged robots, while generally more robust than wheeled robots to locomotion in various terrains (Wetterg...
متن کاملFuzzy landmark-based localization for a legged robot
We describe a new technique for landmark-based self-localization which is suitable for robots with poor odom-etry. This technique uses fuzzy logic to account for errors and imprecision in visual recognition, and for extreme uncertainty in the estimate of the robot's motion. It only requires an approximate model of the sensor system and a qualitative estimate of the robot's displacement , and it...
متن کاملStiffness control of a legged robot equipped with a serial manipulator in stance phase
The ability to perform different tasks by a serial manipulator mounted on legged robots, increases the capabilities of the robot. The position/force control problem of such a robot in the stance phase with point contacts on the ground is investigated here. A target plane with known stiffness is specified in the workspace. Active joints of the legs and serial manipulator are used to exert the de...
متن کامل