Autonomous 3D walking system for a humanoid robot based on visual step recognition and 3D foot step planner

Okada, Kunihiko; Ogura, Takashi; Haneda, A.; Inaba, Masayuki

doi:10.1109/robot.2005.1570187

Cited by 37 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several techniques concentrate on generating only the next movements of the robot [9], [10]. Other approaches plan discrete walking actions on a discretized grid [3], [11]. A drawback of these planning methods is that they are prone to end up in local minima, as their fixed motion primitives (e.g., walking straight, sideways, and turning in 45…”

Section: Related Workmentioning

confidence: 99%

Adaptive level-of-detail planning for efficient humanoid navigation

Hornung

Bennewitz

2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-In this paper, we consider the problem of efficient path planning for humanoid robots by combining grid-based 2D planning with footstep planning. In this way, we exploit the advantages of both frameworks, namely fast planning on grids and the ability to find solutions in situations where gridbased planning fails. Our method computes a global solution by adaptively switching between fast grid-based planning in open spaces and footstep planning in the vicinity of obstacles. To decide which planning framework to use, our approach classifies the environment into regions of different complexity with respect to the traversability. Experiments carried out in a simulated office environment and with a Nao humanoid show that (i) our approach significantly reduces the planning time compared to pure footstep planning and (ii) the resulting plans are almost as good as globally computed optimal footstep paths.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive level-of-detail planning for efficient humanoid navigation

Hornung

Bennewitz

2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…For example, Cupec et al [8] and Yagi and Lumelsky [9] use predefined walking primitives to locally plan paths. Okada et al [10] apply a local planner that generates footsteps along a straight line. A drawback of these local planning methods is that they are prone to end up in local minima on the way to the goal.…”

Section: Related Workmentioning

confidence: 99%

Humanoid navigation with dynamic footstep plans

Garimort

Hornung

Bennewitz

2011

2011 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Humanoid robots possess the capability of stepping over or onto objects, which distinguishes them from wheeled robots. When planning paths for humanoids, one therefore should consider an intelligent placement of footsteps instead of choosing detours around obstacles. In this paper, we present an approach to optimal footstep planning for humanoid robots. Since changes in the environment may appear and a humanoid may deviate from its originally planned path due to imprecise motion execution or slippage on the ground, the robot might be forced to dynamically revise its plans. Thus, efficient methods for planning and replanning are needed to quickly adapt the footstep paths to new situations. We formulate the problem of footstep planning so that it can be solved with the incremental heuristic search method D* Lite and present our extensions, including continuous footstep locations and efficient collision checking for footsteps. In experiments in simulation and with a real Nao humanoid, we demonstrate the effectiveness of the footstep plans computed and revised by our method. Additionally, we evaluate different footstep sets and heuristics to identify the ones leading to the best performance in terms of path quality and planning time. Our D* Lite algorithm for footstep planning is available as open source implementation.

show abstract

“…This section shows the plane segmentation method using 3D points P in (6). The proposed method extracts surfaces for a humanoid robot to walk on an unstructured ground.…”

Section: Plane Segmentationmentioning

confidence: 99%

“…3. The flowchart of the surface extraction from the 3D data P in (6). At the second step, the distance between pairs of the sampled 3D data P s is calculated and the hierarchical cluster tree is created.…”

Section: B Surface Extractionmentioning

confidence: 99%

“…While the laser scanner is used in this paper, almost previous research for a humanoid robot used a stereo camera to extract surface dimensions of an object. K. Okada et al [6] proposed a method to measure the height of one stair in front of a humanoid robot. They apply the 3D hough transformation to extract surface parameters.They also found that the required measurement error of the stair height should be less than 1cm to guarantee the stability of the biped walking on one stair.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ground height map generation for a humanoid robot in an unstructured environment

Park

Kim

You

et al. 2011

IECON 2011 - 37th Annual Conference of the IEEE Industrial Electronics Society

View full text Add to dashboard Cite

This paper proposes a method to measure an accurate ground height map for a humanoid robot by using a laser scanner in an unstructured environment. To measure accurate dimensions of a surface or an obstacle, a 2D laser scanner is installed on the head of a humanoid robot, called MAHRU-1. By moving the head up and down, 3D depth map around a robot is obtained from the 2D range data. After obtaining the 3D depth map around a robot, a plane segmentation method is applied to the 3D data. At first, all the horizontal and vertical planes in the 3D point map are extracted, and the outliers are removed from the plane. After segmenting the plane from the 3D data, the dimensions and the area of the planes are calculated. The accuracy of the extracted surface is evaluated with experimental results, which show the effectiveness of proposed method to extract the surfaces in the unstructured environment.

show abstract

Autonomous 3D walking system for a humanoid robot based on visual step recognition and 3D foot step planner

Cited by 37 publications

References 16 publications

Adaptive level-of-detail planning for efficient humanoid navigation

Adaptive level-of-detail planning for efficient humanoid navigation

Humanoid navigation with dynamic footstep plans

Ground height map generation for a humanoid robot in an unstructured environment

Contact Info

Product

Resources

About