A hierarchical strategy for learning of robot walking strategies in natural terrain environments

Howard, Ayanna M.; Parker, Lonnie T.

doi:10.1109/icsmc.2007.4413682

Cited by 5 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3, was tested in 36 experiments: three different terrain settings at three different light settings, four times each. Since locomotion behavior was assessed by monitoring the robot's forward progress [14], the first experimental setup was to test the displacement recognition and forward progress of the robot in a static environment on solid terrain. The second experimental setup was to test displacement recognition on loose sandy soil.…”

Section: B Experimental Setup and Resultsmentioning

confidence: 99%

Mobility reconfiguration for terrain exploration using passive perception

Brooks

Howard

2009

2009 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

The ability of robotic units to autonomously navigate various terrains is critical to the advancement of robotic operation in natural environments. Next generation robots will need to adapt to their environment in order to accomplish tasks that are either too hazardous, too time consuming, or physically impossible for human-beings. Such tasks may include accurate and rapid explorations of various planets or potentially dangerous areas on Earth. Furthermore, because terrain variability typically increases as the distance that a rover traverses increases, it will be beneficial for robotic units to adapt to their surroundings. As a result, this research investigates a navigation control methodology for a multi-modal locomotive robot based upon passive perception. Surface estimation for robot reconfigurability is implemented using a region growing method, which characterizes the traversability of the terrain, in conjunction with passive perception regarding motion. A mathematical approach is then implemented that inherits human psychological aspects to direct necessary navigation behavior to control robot mobility. Physical experimentations in a simulated Mars yard are presented to validate the methodology.

show abstract

Section: B Experimental Setup and Resultsmentioning

confidence: 99%

Mobility reconfiguration for terrain exploration using passive perception

Brooks

Howard

2009

2009 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Such an approach was proposed as early as at the end of 80's in [8]. The further work on this topic is described in [21]. The DES approach was used for obstacle avoidance [23] and gait generation for multilimbed robots [33].…”

Section: Rough Terrain Negotiationmentioning

confidence: 99%

Terrain Classification and Negotiation with a Walking Robot

Walas

2014

J Intell Robot Syst

View full text Add to dashboard Cite

This paper describes a walking robot controller for negotiation of terrains with different traction characteristics. The feedback is based on three perception systems. The purpose of the presented research is to enhance the autonomy of the walking robot. The information about the class of the terrain allows the robot to work in the real world scenarios more efficiently. In the presented work twelve types of the ground were tested. Suitability of each type of the perception system for characterizing the terrain class was checked. Namely, vision, depth and tactile sensors were used. In each case as a classifier the Support Vector Machines were utilized. The separate classification results from each sensor were combined to obtain better precision and recall in the ground classification process. The information about the terrain type was fed into robot controller to adapt the robot gait parameters. The goal was to achieve good balance between the speed of the movement and the vibration caused by the bounciness and the irregularities of the terrain.The paper begins with the description of the experimental setup. Next, the classification results for each sensor used are presented. Then, the rules of combining classifiers were tested. Finally, the robot gait controller was proposed and evaluated.

show abstract

“…As a consequence, the recalling or shifting of skills becomes smooth and very easier, since they are reconstructed in a same model. There are a few candidates that may be qualified to be such a unified structure in unified modeling achieved robot skills, such as Dynamic Movement Primitive (DMP) model [8,16], while TRBMs seems to be a more ideal choice due to its powerful capacity in feature extraction, knowledge representation as well as efficient and exact inference [11,15,17]. Meanwhile, since all skills could be formulized into one model, too large number of skills (that may bring troubles for memorizing under traditional memory-and-recall method) is no longer a problem.…”

Section: Introductionmentioning

confidence: 99%

Modelling and generalizing achieved robot skills with temporal Restricted Boltzmann Machines

Luo

Han

Wang

et al. 2014

2014 IEEE-RAS International Conference on Humanoid Robots

View full text Add to dashboard Cite

To equip a robot with various required skills so that to serve human society, plenty of research have been performed and successfully applied from both theoretical and practical aspects for decades. Usually, a robot with several skills needs to recall a different controller or model parameters to fit the new circumstance as task to be fulfilled or environment changes. Therefore, how to smoothly shift to a suitable control model to handle changed circumstance becomes an important issue in robotics field. It will be more remarkable when robot skill(s) is extremely environmental sensitive (the skill must be modeled by a specific controller parameter(s) under given certain environment), or when different robot skill is modeled by completely different controller. In this research, a new approach is proposed to model achieved robot skills uniformly, where the modelling process is completed under a unified framework by employing Temporal Restricted Boltzmann Machines (TRBMs), and thus the shifting between different skills becomes more smoothly and easily. In achieving a robot skill, expertise hand tuning and autonomous learning are two commonly used styles, however both of them are still suffer from either boring timeconsuming or high learning computational complexity. As a consequence, how to efficiently achieve a new robot skill is an all-the-time issue to be tackled. In this paper, take the view of utilizing the knowledge that is inherent in those already achieved skills, the generalization of the proposed unified model is investigated. Experimental results on a humanoid robot PKU-HR5.1 suggest that the proposed approach is effective in both modeling and generalizing the achieved robot skills.

show abstract

A hierarchical strategy for learning of robot walking strategies in natural terrain environments

Cited by 5 publications

References 7 publications

Mobility reconfiguration for terrain exploration using passive perception

Mobility reconfiguration for terrain exploration using passive perception

Terrain Classification and Negotiation with a Walking Robot

Modelling and generalizing achieved robot skills with temporal Restricted Boltzmann Machines

Contact Info

Product

Resources

About