Footstep planning of humanoid robot in ROS environment using Generative Adversarial Networks (GANs) deep learning

Mishra, Pradumn; Jain, Urja; Choudhury, Siddharth; Singh, Surjeet; Pandey, Anish; Sharma, Abhishek; Singh, Ramanpreet; Pathak, Vimal Kumar; Saxena, Kuldeep K.; Gehlot, Anita

doi:10.1016/j.robot.2022.104269

Cited by 11 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several studies devoted to the development of original deep learning modules for camera relocalization [82], distance estimation [83], object segmentation [84,85], path planning [86], and scene reconstruction [87]. The architecture of original deep learning modules becomes more complex when multiple deep neural network models are used in serial or parallel pipelines with RNNs or GANs.…”

Section: Discussion and Future Trendsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends

Favorskaya

2023

Electronics

View full text Add to dashboard Cite

Visual Simultaneous Localization and Mapping (VSLAM) has been a hot topic of research since the 1990s, first based on traditional computer vision and recognition techniques and later on deep learning models. Although the implementation of VSLAM methods is far from perfect and complete, recent research in deep learning has yielded promising results for applications such as autonomous driving and navigation, service robots, virtual and augmented reality, and pose estimation. The pipeline of traditional VSLAM methods based on classical image processing algorithms consists of six main steps, including initialization (data acquisition), feature extraction, feature matching, pose estimation, map construction, and loop closure. Since 2017, deep learning has changed this approach from individual steps to implementation as a whole. Currently, three ways are developing with varying degrees of integration of deep learning into traditional VSLAM systems: (1) adding auxiliary modules based on deep learning, (2) replacing the original modules of traditional VSLAM with deep learning modules, and (3) replacing the traditional VSLAM system with end-to-end deep neural networks. The first way is the most elaborate and includes multiple algorithms. The other two are in the early stages of development due to complex requirements and criteria. The available datasets with multi-modal data are also of interest. The discussed challenges, advantages, and disadvantages underlie future VSLAM trends, guiding subsequent directions of research.

show abstract

Section: Discussion and Future Trendsmentioning

confidence: 99%

“…Footstep planning for the indoor navigation of humanoid robots was discussed in [86]. The authors proposed the GAN-based architecture for building an accurate path (even the narrow path) for planning the footsteps of a humanoid robot.…”

Section: Deep Learning Modulesmentioning

confidence: 99%

Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends

Favorskaya

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Due to technological advances, the research and implementation of robotic systems are in constant development, trying to optimize self-control, leading their system to be based on autonomous operations and intelligent decision making [42,43]. Especially for movement, different control methods have been designed that vary according to their field of application; however, the most used is the predictive model, which is based on generating a decision based on statistics, which in turn uses a large amount of data in industrial environments [44][45][46][47][48][49].…”

Section: Related Workmentioning

confidence: 99%

Autonomous Navigation of Robots: Optimization with DQN

et al. 2023

View full text Add to dashboard Cite

In the field of artificial intelligence, control systems for mobile robots have undergone significant advancements, particularly within the realm of autonomous learning. However, previous studies have primarily focused on predefined paths, neglecting real-time obstacle avoidance and trajectory reconfiguration. This research introduces a novel algorithm that integrates reinforcement learning with the Deep Q-Network (DQN) to empower an agent with the ability to execute actions, gather information from a simulated environment in Gazebo, and maximize rewards. Through a series of carefully designed experiments, the algorithm’s parameters were meticulously configured, and its performance was rigorously validated. Unlike conventional navigation systems, our approach embraces the exploration of the environment, facilitating effective trajectory planning based on acquired knowledge. By leveraging randomized training conditions within a simulated environment, the DQN network exhibits superior capabilities in computing complex functions compared to traditional methods. This breakthrough underscores the potential of our algorithm to significantly enhance the autonomous learning capacities of mobile robots.

show abstract

“…1 shows how the sustainable intensification deals when the resources including labour, wages, etc. Furthermore, livestock farming structures are scrutinized due to concerns approximately animal welfare, the effects they have on the environment, and the health risks linked with consuming an excessive amount of meat, even if they greatly contribute to protein-rich diets, jobs, and the preservation of cultural heritage [4]. Fig.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Food Security and Environmental Sustainability via Agroecology and Sustainable Intensification Strategies

Raj,

Kumar,

Sabir

et al. 2024

E3S Web of Conf.

View full text Add to dashboard Cite

The science of ecology is incorporated into farm development and operation through agroecological techniques. A paradigm shift in agriculture is essential to combat hunger, adapt to climate trade, and mitigate environmental degradation. By doing this, researchers may further acknowledge the interdependence of farmed and nonfarmed landscapes and the variety of products and services that robust ecosystems offer, including resilience, nutrient cycling, and pest control, all of which can help sustain yields. Agro-ecology relies heavily on the knowledge and experience of farmers since it fosters independence and decreases reliance on costly outside resources. The concepts of sustainable intensification and agroecology are examined in this paper as additional strategies to address the global issue of increasing food production while lowering environmental impacts. Also, this study evaluates how effectively these approaches boost crop yields, lower environmental costs, and build resilience to climate unpredictability by closely examining existing programs, integrated management strategies, and field experiments. Supporting the findings is a comparative table that shows several techniques of sustainable intensification and how they have an effect on yields and environmental costs. In order to expand resilient, sustainable, and equitable food systems, a discussion of the necessity of a paradigm shift towards agroecological strategies is addressed in the paper's conclusion.

show abstract

Footstep planning of humanoid robot in ROS environment using Generative Adversarial Networks (GANs) deep learning

Cited by 11 publications

References 8 publications

Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends

Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends

Autonomous Navigation of Robots: Optimization with DQN

Optimizing Food Security and Environmental Sustainability via Agroecology and Sustainable Intensification Strategies

Contact Info

Product

Resources

About