Human experience–inspired path planning for robots

Gong, Wenyong; Xie, Xiaohua; Liu, Yong-Jin

doi:10.1177/1729881418757046

Cited by 10 publications

(5 citation statements)

References 30 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Path planning is one of the essential tasks in the automation process of a system that moves in the environment while avoiding obstacles and respecting various constraints [18]. It has been widely applied to lots of scenarios including auto driving, autonomous underwater vehicle control and video games [19]- [22]. It has been widely studied by robot researchers, and plenty of methods have been proposed.…”

Section: A Path Planningmentioning

confidence: 99%

“…Probabilistic path planning algorithms such as Rapidly-exploring random trees [5] and probabilistic roadmaps [25] are also effective methods, which randomly select non-collision points in motion space and then connect them to find the best path. These algorithms don't require any environment modeling, which outperform previous algorithms such as A * in terms of computation cost [22]. Genetic algorithm is another effective path planning problem with high robustness in various scenearios such as robot manipulators and unmanned surface vehicle [26], [27].…”

Section: A Path Planningmentioning

confidence: 99%

See 1 more Smart Citation

Capability Iteration Network for Robot Path Planning

Nie,

Gao,

Mei

et al. 2021

Preprint

View full text Add to dashboard Cite

Path planning is an important topic in robotics. Recently, value iteration based deep learning models have achieved good performance such as Value Iteration Network(VIN). However, previous methods suffer from slow convergence and low accuracy on large maps, hence restricted in path planning for agents with complex kinematics such as legged robots. Therefore, we propose a new value iteration based path planning method called Capability Iteration Network(CIN). CIN utilizes sparse reward maps and encodes the capability of the agent with state-action transition probability, rather than a convolution kernel in previous models. Furthermore, two training methods including end-toend training and training capability module alone are proposed, both of which speed up convergence greatly. Several path planning experiments in various scenarios, including on 2D, 3D grid world and real robot with different map sizes are conducted. The results demonstrate that CIN has higher accuracy, faster convergence and lower sensitivity to random seed compared to previous VI-based models, hence more applicable for real robot path planning.

show abstract

Section: A Path Planningmentioning

confidence: 99%

Section: A Path Planningmentioning

confidence: 99%

Capability Iteration Network for Robot Path Planning

Nie,

Gao,

Mei

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This method involves pushing the soil from a high level to a low level, such that the bulldozer is on a higher surface for a longer time. Based on the summarised work experience of skilled operators, we know that the mound closest to the bulldozer will be levelled first, and the other mounds will then be levelled [50]. Accordingly, the state of the bulldozer can be categorised as a state of work and movement.…”

Section: Feedback Controlmentioning

confidence: 99%

Assessment and Feedback Control of Paving Quality of Earth-Rock Dam Based on OODA Loop

Wang

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

Paving thickness and evenness are two key factors that affect the paving operation quality of earth-rock dams. However, in the recent study, both of the key factors characterising the paving quality were measured using finite point random sampling, which resulted in subjectivity in the detection and a lag in the feedback control. At the same time, the on-site control of the paving operation quality based on experience results in a poor and unreliable paving quality. To address the above issues, in this study, a novel assessment and feedback control framework for the paving operation quality based on the observe–orient–decide–act (OODA) loop is presented. First, in the observation module, a cellular automaton is used to convert the location of the bulldozer obtained by monitoring devices into the paving thickness of the levelling layer. Second, in the orient module, the learning automaton is used to update the state of the corresponding and surrounding cells. Third, in the decision module, an overall path planning method is developed to realise feedback control of the paving thickness and evenness. Finally, in the act module, the paving thickness and evenness of the entire work unit are calculated and compared to their control thresholds to determine whether to proceed with the next OODA loop. The experiments show that the proposed method can maintain the paving thickness less than the designed standard value and effectively prevent the occurrence of ultra-thick or ultra-thin phenomena. Furthermore, the paving evenness is improved by 21.5% as compared to that obtained with the conventional paving quality control method. The framework of the paving quality assessment and feedback control proposed in this paper has extensive popularisation and application value for the same paving construction scene.

show abstract

“…This benefits from the fact that optimal paths designed by path planning algorithms can satisfy various requirements in different scenarios. Therefore, path planning is one of the central components for many real-world applications including autonomous driving [1], smart service robots [2,3,4,5], and unmanned aerial vehicles (UAV) [6,7].…”

Section: Introductionmentioning

confidence: 99%

Biharmonic navigation using radial basis functions

Fan

Gong

2021

Robotica

Self Cite

View full text Add to dashboard Cite

Path planning has been widely investigated by many researchers and engineers for its extensive applications in the real world. In this paper, a biharmonic radial basis potential function (BRBPF) representation is proposed to construct navigation fields in 2D maps with obstacles, and it therefore can guide and design a path joining given start and goal positions with obstacle avoidance. We construct BRBPF by solving a biharmonic equation associated with distance-related boundary conditions using radial basis functions (RBFs). In this way, invalid gradients calculated by finite difference methods in large size grids can be preventable. Furthermore, paths constructed by BRBPF are smoother than paths constructed by harmonic potential functions and other methods, and plenty of experimental results demonstrate that the proposed method is valid and effective.

show abstract

Human experience–inspired path planning for robots

Cited by 10 publications

References 30 publications

Capability Iteration Network for Robot Path Planning

Capability Iteration Network for Robot Path Planning

Assessment and Feedback Control of Paving Quality of Earth-Rock Dam Based on OODA Loop

Biharmonic navigation using radial basis functions

Contact Info

Product

Resources

About