Autonomous Robotic Tissue Palpation and Abnormalities Characterisation via Ergodic Exploration

TL;DR

The proposed autonomous robotic palpation framework for real-time elastic mapping during tissue exploration using a viscoelastic tissue model achieves better reconstruction accuracy, enhanced segmentation capability, and improved robustness in detecting stiff inclusions compared to Bayesian Optimisation-based techniques.

Abstract

We propose a novel autonomous robotic palpation framework for real-time elastic mapping during tissue exploration using a viscoelastic tissue model. The method combines force-based parameter estimation using a commercial force/torque sensor with an ergodic control strategy driven by a tailored Expected Information Density, which explicitly biases exploration toward diagnostically relevant regions by jointly considering model uncertainty, stiffness magnitude, and spatial gradients. An Extended Kalman Filter is employed to estimate viscoelastic model parameters online, while Gaussian Process Regression provides spatial modelling of the estimated elasticity, and a Heat Equation Driven Area Coverage controller enables adaptive, continuous trajectory planning. Simulations on synthetic stiffness maps demonstrate that the proposed approach achieves better reconstruction accuracy, enhanced segmentation capability, and improved robustness in detecting stiff inclusions compared to Bayesian Optimisation-based techniques. Experimental validation on a silicone phantom with embedded inclusions emulating pathological tissue regions further corroborates the potential of the method for autonomous tissue characterisation in diagnostic and screening applications.

Figures (5)

• Figure 1: Experimental setup for the proposed ergodic search: (bottom-left) silicone sample; (top-left) ground-truth elasticity map obtained using a grid-based approach; (right) the robotic manipulator palpating the silicone sample.
• Figure 2: Synthetic elasticity distributions for simulated scenarios, from 1 to 3 stiffer regions. The colour scale refers to the elastic modulus (in kPa).
• Figure 3: End-effector tip trajectory during the exploration of an elasticity distribution with three stiff regions: comparison of different planners. The cyan circle indicates the beginning of the trajectory, while the magenta square denotes the end of the trajectory. In plots (b) and (c), the orange markers indicate the locations selected by BO, whereas the red markers represent the sampled points collected along the executed trajectory.
• Figure 4: Clustering and boundary extraction results after the exploration phase. The original shapes (in blue) are shown alongside the estimated ones (in red).
• Figure 5: Estimated stiffness distribution obtained through palpation of the soft phantom. The stiffer region is shown in yellow. The end-effector trajectory during the search motion is visualised using a grayscale gradient, from black (beginning) to white (end).