I have completed Ph.D. from National Institute of Technology, Rourkela, Odisha, India. I am engaged with research areas contains humanoid robot stabilization, gait synthesis and path planning using soft computing techniques.
Integrated framework utilizing scene text detection and recognition techniques for enhancing point of interest extraction from name boards in all Indic languages Abhishek Kumar Kashyap, Mahima Upadhya, Vikas Singh Panwar, Vikrant Chandrakar Scientific Reports, 2026 This paper focused on enhancing text recognition, script identification, language classification, and point of interest (POI) extraction from images captured by Mobile Mapping Systems (MMS). The initiative was undertaken to improve the existing Computer vision-based artificial intelligence modules. The advancements made is to be contributed to the system’s implementation, bringing improved functionality and accuracy to the system. The current system, called Text Detection and Recognition (TDR), consists of several neural modules operating in sequential stages. The first module identifies areas of interest within the MMS images, focusing on shop signboards, traffic signs, and directional boards. The second stage involves detecting text words within these areas and cropping the relevant pixels from the image. These cropped images are then processed in the third stage, where the language script is detected, identifying one of ten Indian scripts. In the fourth stage, specific character recognizers corresponding to the identified script are used to recognize the text. The outputs from these stages are aggregated into a correlated JSON output. Additionally, a parallel fifth stage detects various fields within the MMS images, such as name, address, pin, icon, phone and GSTIN number, ultimately extracting a comprehensive human-readable address for any POI from the MMS image. The primary focus includes investigating novel text recognition algorithms to improve accuracy and efficiency, exploring various script identification algorithms to enhance language classification capabilities, implementing a dictionary-based approach for more accurate word detection, and developing methods for correcting the words that the CRNN model predicts to reduce errors. This work is novel because it combines word correction, OCR, detection, classification, and POI field extraction into a single pipeline designed specifically for Indic scripts. By obtaining 96.17% script recognition accuracy, 92.5% word accuracy, and 33% average precision in POI detection, the suggested framework outperforms previous benchmarks like IndicText (93.6%) and transformer-based OCR (88.5%).
Stable Walking and Dynamic Obstacle Avoidance of Humanoid Robots Using Optimized Step Planner Abhishek Kumar Kashyap, Dayal R. Parhi International Journal of Humanoid Robotics, 2026 Developing and maintaining a collision-free trajectory is one of the most challenging tasks for autonomous robotics in unpredictable and dynamic situations. This work describes the development of a mechanism for navigating humanoid robots. Sensors are used to determine the positioning of the developed system. The breadth-first search algorithm has yielded positive results in the task of step adjustment to avoid dynamic barriers. Rule-based machine learning provides two driving angles based on the position evaluation of static and moving barriers and the goal. Further, the footstep is optimized based on the JAYA algorithm. It takes the outputs of machine learning as its input and provides an optimum driving angle to avoid static and dynamic barriers and generates a smooth trajectory. The proposed step planner is integrated into humanoid NAO for autonomous navigation. For avoiding dynamic barriers (same robot), a separate algorithm is required that will solve the conflicts during navigation. In this paper, the dining philosopher controller is used. For evaluating the robustness of the proposed controller, various types of scenarios have been adapted. These environments are static with a single target, static with multiple targets, environments with dynamic obstacles and multiple robots in a single environment. It is evaluated in simulated environments and verified in experimental environments. The deviation observed is under 5% that displays a validated relationship between them. Its acceptability is demonstrated based on torque generation at different joints in reference to the default controller of humanoid NAO. Ultimately, the robustness of the proposed step planner is evaluated by comparing it with a conventional path planner in a dynamic environment where it shows superiority.
A study on different methods to change the Rayleigh number in the analysis of heat transfer Vikrant Chandrakar, Atul Bhattad, Priyaranjan Samal, Jnana Ranjan Senapati, Abhishek Kumar Kashyap Scientific Reports, 2025 This study provides awareness about natural convection and associated non-dimensional numbers like the Prandtl number, Grashof number, Rayleigh number, and Reynolds number. The main focus of this research is to present the different methods employed to vary the Rayleigh number $$\\:\\left(Ra\\right)$$ in an extensive range. The research concludes that changing the gravity value to obtain the considerable variation in $$\\:Ra$$ is also a possible method for conducting the numerical analysis and observing the impact of the Rayleigh number. The validation of the numerical scheme with existing literature is provided here. An attempt is made to show that similar effects could be obtained by changing the value of gravity and the body’s characteristics length. The comparative results obtained by changing length and gravity are presented which gives almost the same result $$\\:(\\pm\\:\\:10\\%\\:$$ error) to get the same $$\\:Ra$$ . This presents the beauty of a non-dimensional study. Moreover, it is possible to say that in the non-dimensional analysis of engineering practice, the individual variables that are changed are not important considering the non-dimensional results.
Human-inspired dynamic obstacle and inter-collision avoidance algorithm for humanoid biped robots Abhishek Kumar Kashyap, Dayal Parhi Robotics and Autonomous Systems, 2025 In order to maximize humanoid robot navigation, this paper introduces the Enhanced DAYANI Arc Contour Intelligent (EDACI) Method, which integrates Dynamic Window Approach (DWA) to choose the best walking parameters for avoiding obstacles and smooth trajectory management. EDACI algorithm provides the best response to guide humanoid robots to the goal by avoiding obstacles and preparing a smooth trajectory. Further, DWA optimizes the walking pattern of humanoid robots by controlling their velocity while encountering an obstacle and finding a smooth trajectory. The performance of the proposed controller is examined by implementing it in humanoid NAOs for navigation in several simulated and experimental terrains. It is implemented on a single humanoid robot for navigation in static and dynamic environments and on multiple humanoid robots on a single platform. Navigation of multiple robots has to deal with the situation of conflict where one robot behaves as a dynamic obstacle to the other. It is solved by setting a Dining Philosopher Controller (DPC) in the base technique. The results obtained from the simulations and experiments have a divergence below 5 %, which demonstrates a satisfactory relation between them. The proposed controller's efficacy is demonstrated by comparing the torque developed at different joints with contrast to the inbuilt controller of NAO. The results show good improvement in torque produced at all joints. In addition, it is compared with an existing controller for navigation, which displays superiority of the proposed controller.
Multi-Objective Route Outlining and Collision Avoidance of Multiple Humanoid Robots in a Cluttered Environment Abhishek Kumar Kashyap, Dayal R. Parhi Journal of Field Robotics, 2025 In robotics, navigating a humanoid robot through a cluttered environment is challenging. The present study aims to enhance the footstep and determine optimal paths regarding the robot's route length. The objective function for navigation of multiple humanoid robots is presented to optimize the route length and travel time. A hybrid technique using a probabilistic roadmap (PRM) and firefly algorithm (FA) is presented for humanoid robot navigation in a cluttered environment with static and dynamic obstacles. Sensory information, such as barrier range in the left, right, and front directions, is fed into the PRM framework that allows the humanoid robot to walk steadily with an initial steering angle. It finds the shortest path using the Bellman–Ford algorithm. The FA technique is used for efficient guidance and footstep modification in a cluttered environment to find a smooth and optimized path. To avoid static obstacles, the suggested hybrid technique provides optimum steering angles and ensures the minimum route length by taking the output of PRM as its input. A 3D simulator and a real‐world environment have been used for simulation and experiment in a cluttered environment utilizing the developed model and standalone methods. The humanoid robot achieves the target in all scenarios, but the FA‐tuned PRM technique is advantageous to this purpose, as shown by the convergence curve, route length, and travel duration. Multiple humanoid robot navigation has an additional self‐collision issue, which is eliminated by employing a dining philosopher controller as the base technique. In addition, the proposed controller is evaluated in contrast to the existing technique. The developed strategy ensures effectiveness and efficacy depending on these findings.
A systematic Review on Humanoid Biped Robot: History, Design, Gait Analysis and Path Planning in Various Terrains Abhishek Kumar Kashyap, Dayal R. Parhi Evergreen, 2025 Because of its capacity to replicate human behavior and maneuver through challenging circumstances, humanoid robots have drawn a lot of interest.An overview of the literature that refers to history, kinematic analysis, dynamic analysis, gait stabilization and trajectory plan approaches for humanoid robots on even, uneven are presented in this paper.The study emphasizes on conventional techniques like fuzzy logic and artificial potential fields as well as methods inspired by nature, such as teaching-learning-based optimization, dynamic window approach, and ant colony optimization.It has been demonstrated that hybrid approaches, which combine classical and nature-based algorithms, improve flexibility and dependability in both static and dynamic contexts.The results show that when it comes to developing effective and reliable path planning, hybrid techniques perform better than traditional tactics.A roadmap for upcoming developments in model innovation and guidance tactics is provided by identifying key research needs in humanoid robotics.
Autonomous navigation of ROS2 based Turtlebot3 in static and dynamic environments using intelligent approach Abhishek Kumar Kashyap, Kavya Konathalapalli International Journal of Information Technology Singapore, 2025 This study offers a unique strategy for autonomous navigation for the TurtleBot3 robot by applying advanced reinforcement learning algorithms in both static and dynamic environments. With the use of TD3 (twin-delayed deep deterministic), DDPG (Deep Deterministic Policy Gradient), and DQN (Deep Q-Network), real-time object detection, tracking, and navigation can now be done seamlessly by the proposed TD3 algorithms. Additional techniques have been integrated to this project to enhance its mobility performance: ROS 2 (Robot Operating System 2) and LiDAR (Light Detection and Ranging)-based perception. Performance comparison among the above-mentioned algorithms shows that TD3 is the most efficient and robust when exposed to diverse environments. The work further addresses significant gaps in dynamic obstacle navigation and maze resolution, significantly changing the game for robotics applications such as those found in surveillance, human–robot interaction, and inspection. The outcome significantly boosts TurtleBot3's performance and capabilities across various scenarios.
Hybrid Metaheuristic-Machine Learning Algorithms for Inter-Collision Avoidance of Multiple Humanoid Robots Abhishek Kumar Kashyap, Dayal R. Parhi, Bhumeshwar K. Patle Metaheuristics in Engineering Applications, 2025 Scientists find humanoid (human-alike) robots to be a fascinating topic. A capable biped robot is currently accessible and offers good value for experimental labs and the public, thanks to the development of humanoid robots. In this chapter, a hybrid algorithm has been developed and implemented in multiple robot navigation assignments. The algorithm is a combination of a metaheuristic algorithm, such as particle swarm optimization (PSO), and a machine learning algorithm such as random forest. The PSO algorithm provides an initial turning angle but can be trapped in local minima. Therefore, to avoid this scenario, the random forest technique has been implemented. It selects the best possible path using the probability method. The hybrid algorithm is implemented on two NAO humanoid robots to evaluate its robustness. The controller is tested in simulated and experimental workspaces and further compared based on path length and time taken. The results demonstrate that the relation between simulation and real-time experiments is under 5%.
Stable Walking and Dynamic Obstacle Avoidance of Humanoid Robots Using Optimized Step Planner AK Kashyap, DR Parhi International Journal of Humanoid Robotics, 2640009 , 2026 2026
Integrated framework utilizing scene text detection and recognition techniques for enhancing point of interest extraction from name boards in all Indic languages AK Kashyap, M Upadhya, VS Panwar, V Chandrakar Scientific Reports , 2026 2026
Reactive Avoidance of Obstacles by a Quadrotor using 3𝐷 Collision Cones in Multiple Settings A Kashyap, O Samir, R Rijal, R Gyawali, A Chakravarthy 2026
Reactive Avoidance of Obstacles by a Quadrotor using 3D Collision Cones in Multiple Settings A Kashyap, O Samir, R Rijal, R Gyawali, A Chakravarthy AIAA SCITECH 2026 Forum, 1980 , 2026 2026
Path optimization of biped humanoid robot on inclined surface employing 3D-MDSLIP framework AK Kashyap, DR Parhi International Journal on Interactive Design and Manufacturing (IJIDeM), 1-18 , 2025 2025
Human-inspired dynamic obstacle and inter-collision avoidance algorithm for humanoid biped robots AK Kashyap, D Parhi Robotics and Autonomous Systems 191, 105023 , 2025 2025 Citations: 3
A study on different methods to change the Rayleigh number in the analysis of heat transfer V Chandrakar, A Bhattad, P Samal, JR Senapati, AK Kashyap Scientific Reports 15 (1), 25773 , 2025 2025 Citations: 3
Multi‐Objective Route Outlining and Collision Avoidance of Multiple Humanoid Robots in a Cluttered Environment AK Kashyap, DR Parhi Journal of Field Robotics 42 (4), 952-969 , 2025 2025
Autonomous navigation of ROS2 based turtlebot3 in static and dynamic environments using intelligent approach AK Kashyap, K Konathalapalli International Journal of Information Technology, 1-23 , 2025 2025 Citations: 11
A systematic Review on Humanoid Biped Robot: History, Design, Gait Analysis and Path Planning in Various Terrains DRP Abhishek Kumar Kashyap Evergreen 12 (1), 362-386 , 2025 2025 Citations: 2
Mapping and Navigation of Custom Robot Using Improved A* Algorithm O Magadum, AK Kashyap International Conference on Robotics, Control, Automation and Artificial … , 2024 2024
Dynamic posture stabilization of humanoid robot NAO using 3D-multilinked dual spring-loaded inverted pendulum model for uneven and inclined floor AK Kashyap, DR Parhi International Journal of Humanoid Robotics 20 (04), 2350007 , 2023 2023 Citations: 7
A review on path planning AI techniques for mobile robots S Deshpande, AK Kashyap, BK Patle Robotic Systems and Applications 3 (1), 27-46 , 2023 2023 Citations: 17
Dynamic walking of multi-humanoid robots using BFGS Quasi-Newton method aided artificial potential field approach for uneven terrain: AK Kashyap, DR Parhi AK Kashyap, DR Parhi Soft Computing 27 (9), 5893-5910 , 2023 2023 Citations: 16
Humanoid robot path planning using memory-based gravity search algorithm and enhanced differential evolution approach in a complex environment DR Parhi, AK Kashyap Expert Systems with Applications 215, 119423 , 2023 2023 Citations: 22
Modified type-2 fuzzy controller for intercollision avoidance of single and multi-humanoid robots in complex terrains AK Kashyap, DR Parhi Intelligent Service Robotics 16 (1), 87-108 , 2023 2023 Citations: 4
Navigation for multi-humanoid using MFO-aided reinforcement learning approach AK Kashyap, DR Parhi, V Kumar Robotica 41 (1), 346-369 , 2023 2023 Citations: 12
Dynamic walking of humanoid robot on flat surface using amplified LIPM plus flywheel model AK Kashyap, DR Parhi International Journal of Intelligent Unmanned Systems 10 (4), 316-329 , 2022 2022 Citations: 9
Gravity search algorithm-based path planning of single humanoid based on the study of different artificial intelligence techniques Vikas, DR Parhi, AK Kashyap, B Deepak Recent Trends in Product Design and Intelligent Manufacturing Systems … , 2022 2022 Citations: 3
Stable locomotion of humanoid robots on uneven terrain employing enhanced DAYANI arc contour intelligent algorithm AK Kashyap, DR Parhi Journal of Autonomous Vehicles and Systems 2 (4), 041002 , 2022 2022 Citations: 4
MOST CITED SCHOLAR PUBLICATIONS
Particle swarm optimization aided PID gait controller design for a humanoid robot AK Kashyap, DR Parhi ISA transactions 114, 306-330 , 2021 2021 Citations: 113
A hybrid technique for path planning of humanoid robot NAO in static and dynamic terrains AK Kashyap, DR Parhi, MK Muni, KK Pandey Applied Soft Computing 96, 106581 , 2020 2020 Citations: 83
Autonomous mobile robot navigation between static and dynamic obstacles using multiple ANFIS architecture A Pandey, AK Kashyap, DR Parhi, BK Patle World Journal of Engineering 16 (2), 275-286 , 2019 2019 Citations: 78
Optimization of stability of humanoid robot NAO using ant colony optimization tuned MPC controller for uneven path: AK Kashyap, DR Parhi AK Kashyap, DR Parhi Soft Computing 25 (7), 5131-5150 , 2021 2021 Citations: 48
Dynamic stabilization of NAO humanoid robot based on whole-body control with simulated annealing AK Kashyap, DR Parhi, S Kumar International Journal of Humanoid Robotics 17 (03), 2050014 , 2020 2020 Citations: 47
Static and dynamic path optimization of multiple mobile robot using hybridized fuzzy logic-whale optimization algorithm S Kumar, DR Parhi, AK Kashyap, MK Muni Proceedings of the Institution of Mechanical Engineers, Part C: Journal of … , 2021 2021 Citations: 38
Different Nature-Inspired Techniques Applied for Motion Planning of Wheeled Robot: A Critical Review A Abhishek kumar kashyap International Journal of Advanced Robotics and Automation 3 (1), 1-10 , 2018 2018 Citations: 35
Multi-objective trajectory planning of humanoid robot using hybrid controller for multi-target problem in complex terrain AK Kashyap, DR Parhi Expert Systems with Applications 179, 115110 , 2021 2021 Citations: 30
Multi-objective optimization technique for trajectory planning of multi-humanoid robots in cluttered terrain AK Kashyap, DR Parhi, A Pandey ISA transactions 125, 591-613 , 2022 2022 Citations: 25
Optimized Path Planning for Three-Wheeled Autonomous Robot Using Teaching–Learning-Based Optimization Technique AK Kashyap, A Pandey Advances in Materials and Manufacturing Engineering, 49-57 , 2020 2020 Citations: 25
Humanoid robot path planning using memory-based gravity search algorithm and enhanced differential evolution approach in a complex environment DR Parhi, AK Kashyap Expert Systems with Applications 215, 119423 , 2023 2023 Citations: 22
Spider monkey optimization algorithm based collision-free navigation and path optimization for a mobile robot in the static environment KP Lagaza, AK Kashyap, A Pandey Advances in Mechanical Engineering: Select Proceedings of ICRIDME 2018, 1459 … , 2020 2020 Citations: 22
A review on path planning AI techniques for mobile robots S Deshpande, AK Kashyap, BK Patle Robotic Systems and Applications 3 (1), 27-46 , 2023 2023 Citations: 17
Obstacle avoidance and path planning of humanoid robot using fuzzy logic controller aided owl search algorithm in complicated workspaces AK Kashyap, DR Parhi Industrial Robot: the international journal of robotics research and … , 2022 2022 Citations: 17
Controlled gait planning of humanoid robot NAO based on 3D-LIPM model AK Kashyap, A Pandey, A Chhotray, DR Parhi International Conference on Artificial Intelligence in Manufacturing … , 2019 2019 Citations: 17
Dynamic walking of multi-humanoid robots using BFGS Quasi-Newton method aided artificial potential field approach for uneven terrain: AK Kashyap, DR Parhi AK Kashyap, DR Parhi Soft Computing 27 (9), 5893-5910 , 2023 2023 Citations: 16
Improved modified chaotic invasive weed optimization approach to solve multi-target assignment for humanoid robot AK Kashyap, D Parhi, A Pandey Journal of Robotics and Control (JRC) 2 (3), 194-199 , 2021 2021 Citations: 16
Dynamic Path Planning for Autonomous Mobile Robot using Minimum Fuzzy Rule Based Controller with Avoidance of Moving Obstacles AK Kashyap, KP Lagaza, A Pandey 2018 International Conference on Recent Innovations in Electrical … , 2020 2020 Citations: 13
Navigation for multi-humanoid using MFO-aided reinforcement learning approach AK Kashyap, DR Parhi, V Kumar Robotica 41 (1), 346-369 , 2023 2023 Citations: 12
Autonomous navigation of ROS2 based turtlebot3 in static and dynamic environments using intelligent approach AK Kashyap, K Konathalapalli International Journal of Information Technology, 1-23 , 2025 2025 Citations: 11