RobKiNet: Robotic Kinematics Informed Neural Network for Optimal Robot Configuration Prediction

2024-02-26

AI Summary

To address the low search efficiency in continuous configuration space for Task and Motion Planning (TAMP), this paper proposes a lightweight neural network framework incorporating kinematic priors, comprising a loosely coupled Chassis Motion Predictor (CMP) and a Full-Body Motion Predictor (FMP). We innovatively embed forward and inverse kinematic constraints into CMP and FMP, respectively, enabling knowledge-guided end-to-end configuration regression; contrastive learning is further introduced to enhance data efficiency. Experiments demonstrate that CMP and FMP achieve configuration prediction accuracies of 96.67% and 98%, respectively, and accelerate motion planning by factors of 24.24× and 153×. Crucially, training data requirements are reduced to only 1/71 and 1/15,052 of those needed by comparable deep learning approaches. The framework thus significantly improves accuracy, computational speed, and generalization capability in TAMP.

Technology Category

Intelligent Robots: Motion and Path PlanningHumans and AI: Human-Aware Planning and Behavior PredictionPlanning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Task and Motion Planning (TAMP) is essential for robots to interact with the world and accomplish complex tasks. The TAMP problem involves a critical gap: exploring the robot's configuration parameters (such as chassis position and robotic arm joint angles) within continuous space to ensure that task-level global constraints are met while also enhancing the efficiency of subsequent motion planning. Existing methods still have significant room for improvement in terms of efficiency. Recognizing that robot kinematics is a key factor in motion planning, we propose a framework called the Robotic Kinematics Informed Neural Network (RobKiNet) as a bridge between task and motion layers. RobKiNet integrates kinematic knowledge into neural networks to train models capable of efficient configuration prediction. We designed a Chassis Motion Predictor(CMP) and a Full Motion Predictor(FMP) using RobKiNet, which employed two entirely different sets of forward and inverse kinematics constraints to achieve loosely coupled control and whole-body control, respectively. Experiments demonstrate that CMP and FMP can predict configuration parameters with 96.67% and 98% accuracy, respectively. That means that the corresponding motion planning can achieve a speedup of 24.24x and 153x compared to random sampling. Furthermore, RobKiNet demonstrates remarkable data efficiency. CMP only requires 1/71 and FMP only requires 1/15052 of the training data for the same prediction accuracy compared to other deep learning methods. These results demonstrate the great potential of RoboKiNet in robot applications.

Problem

• Efficient robot configuration prediction for task and motion planning.
• Integration of kinematic knowledge into neural networks for accuracy.
• Reduction in training data requirements for deep learning methods.

Innovation

• RobKiNet integrates kinematics into neural networks.
• CMP and FMP predict configurations with high accuracy.
• RobKiNet significantly reduces required training data.