18417504. ROBOTIC NAVIGATION WITH SIMULTANEOUS LOCAL PATH PLANNING AND LEARNING simplified abstract (Tata Consultancy Services Limited)

From WikiPatents
Revision as of 06:07, 1 October 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

ROBOTIC NAVIGATION WITH SIMULTANEOUS LOCAL PATH PLANNING AND LEARNING

Organization Name

Tata Consultancy Services Limited

Inventor(s)

Arup Kumar Sadhu of Kolkata (IN)

Lokesh Kumar of Kolkata (IN)

Ranjan Dasgupta of Kolkata (IN)

Mohit Ludhiyani of Kolkata (IN)

Titas Bera of Kolkata (IN)

ROBOTIC NAVIGATION WITH SIMULTANEOUS LOCAL PATH PLANNING AND LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18417504 titled 'ROBOTIC NAVIGATION WITH SIMULTANEOUS LOCAL PATH PLANNING AND LEARNING

Simplified Explanation

The patent application describes a method and system for robotic navigation that combines local path planning and learning simultaneously to improve overall system performance.

  • The planner acts as an actuator to balance exploration and exploitation in the learning algorithm.
  • The synergy between Dynamic Window Approach (DWA) as a planning algorithm and Next Best Q-learning (NBQ) as a learning algorithm offers an efficient local planning solution.
  • The NBQ algorithm has a dynamic Q-tree dimension, eliminating the need to define parameters beforehand.

Key Features and Innovation

  • Simultaneous local path planning and learning in robotic navigation.
  • Planner acts as an actuator to assist in balancing exploration and exploitation.
  • Dynamic Window Approach (DWA) and Next Best Q-learning (NBQ) algorithms work together efficiently.
  • NBQ algorithm features a dynamic Q-tree dimension for improved performance.

Potential Applications

This technology can be applied in autonomous robots, drones, self-driving vehicles, and other navigation systems that require real-time planning and learning capabilities.

Problems Solved

  • Traditional robot navigation techniques lack coordination between learning and planning algorithms.
  • Balancing exploration and exploitation in learning algorithms can be challenging without proper guidance.
  • Defining parameters beforehand in learning algorithms can limit adaptability and efficiency.

Benefits

  • Improved overall system performance in robotic navigation.
  • Enhanced coordination between planning and learning algorithms.
  • Efficient local path planning solution for real-time applications.
  • Dynamic Q-tree dimension in NBQ algorithm allows for adaptability and flexibility.

Commercial Applications

  • Autonomous robots and drones for navigation in dynamic environments.
  • Self-driving vehicles for real-time path planning and learning.
  • Industrial robots for efficient movement and navigation in complex spaces.

Questions about Robotic Navigation

How does the synergy between DWA and NBQ algorithms improve local planning efficiency?

The Dynamic Window Approach (DWA) and Next Best Q-learning (NBQ) algorithms work together to balance exploration and exploitation, resulting in more efficient local path planning.

What are the potential applications of this technology beyond robotic navigation?

This technology can be applied in various fields such as artificial intelligence, optimization algorithms, and real-time decision-making systems for improved performance and adaptability.


Original Abstract Submitted

In conventional robot navigation techniques learning and planning algorithms act independently without guiding each other simultaneously. A method and system for robotic navigation with simultaneous local path planning and learning is disclosed. The method discloses an approach to learn and plan simultaneously by assisting each other and improve the overall system performance. The planner acts as an actuator and helps to balance exploration and exploitation in the learning algorithm. The synergy between dynamic window approach (DWA) as a planning algorithm and a disclosed Next best Q-learning (NBQ) as a learning algorithm offers an efficient local planning algorithm. Unlike the traditional Q-learning, dimension of Q-tree in the NBQ is dynamic and does not require to define a priori.