IK Seed Generator for Dual-Arm Human-like Physicality Robot with Mobile Base

TL;DR

The paper tackles inverse kinematics for compact, human-like robots with a mobile base by proposing an offline IK seed-generation framework that combines a scaled-Jacobian goodness metric $f = \sqrt{\det(\tilde{\mathbf{J}}(\mathbf{q}) \tilde{\mathbf{J}}(\mathbf{q})^{T})}$, a reachability-map–driven arm-state enumeration, and a genetic algorithm to optimize trunk/base configurations. The Arm-Initial-Guess Provider supplies arm-state candidates; the IK Seed Generator searches for seeds offline, enabling efficient online IK solving and extending naturally to dual-arm manipulation. Quantitative experiments on Seednoid demonstrate high IK success rates in grasping and pouring scenarios, validating improvements in robustness against joint limits and environmental perturbations. The results support practical deployment of the method for three典 application kinds: varied approach directions, pouring with two arms, and regrasp-based reorientation, highlighting the method’s potential to enhance real-world household manipulation with humanoid robots.

Abstract

Robots are strongly expected as a means of replacing human tasks. If a robot has a human-like physicality, the possibility of replacing human tasks increases. In the case of household service robots, it is desirable for them to be on a human-like size so that they do not become excessively large in order to coexist with humans in their operating environment. However, robots with size limitations tend to have difficulty solving inverse kinematics (IK) due to mechanical limitations, such as joint angle limitations. Conversely, if the difficulty coming from this limitation could be mitigated, one can expect that the use of such robots becomes more valuable. In numerical IK solver, which is commonly used for robots with higher degrees-of-freedom (DOF), the solvability of IK depends on the initial guess given to the solver. Thus, this paper proposes a method for generating a good initial guess for a numerical IK solver given the target hand configuration. For the purpose, we define the goodness of an initial guess using the scaled Jacobian matrix, which can calculate the manipulability index considering the joint limits. These two factors are related to the difficulty of solving IK. We generate the initial guess by optimizing the goodness using the genetic algorithm (GA). To enumerate much possible IK solutions, we use the reachability map that represents the reachable area of the robot hand in the arm-base coordinate system. We conduct quantitative evaluation and prove that using an initial guess that is judged to be better using the goodness value increases the probability that IK is solved. Finally, as an application of the proposed method, we show that by generating good initial guesses for IK a robot actually achieves three typical scenarios.

Figures (12)

• Figure 1: More complicated operations: manipulation with both arms, such as pouring and regrasping and grasping with both hands
• Figure 2: Examples of difficult situations to adjust hand configurations. In case (a), due to the joint limit of the elbow, it is difficult to move the hand to the right using the shoulder joint only. In case (b), the arm is almost extended and the arm cannot move any further.
• Figure 3: Seednoid
• Figure 4: First scenario: grasp from the x-direction.
• Figure 5: Second scenario: pouring motion