Ahsan Tanveer

Underwater manipulation often occurs under degraded visibility due to turbidity, glare, and gripper occlusion, limiting the reliability of vision-based perception during approach and grasping. In such settings, soft grippers are well suited for compliant interaction, but they typically lack an onboard pre-contact cue that can guide approach and closure when vision is unreliable. This extended abstract explores active electrosense as a lightweight sensing modality that can provide a proximity-like signal prior to contact by measuring perturbations of an applied electric field in conductive media. We instrument an octopus-inspired gripper with a discrete electrode layout and record multi-channel sensing voltages using off-the-shelf hardware. Simulation and tank experiments with a suspended conductive sphere show structured, object-dependent changes in the multi-electrode voltage readout relative to empty-water baselines, with detectability varying across excitation of 5 to 20 V and frequencies from 1 mHz to 1 kHz. These findings motivate systematic investigation of gripper-integrated electrosense as a complementary pre-contact cue for underwater soft manipulation.

Multi-step motion prediction for continuum robots is difficult, especially under actuation distribution shift, where error accumulation can distort the predicted steady response and destabilize rollouts. This paper introduces a hybrid equilibriumanchored residual-learning framework for a tendon-driven 3D continuum arm that makes steady behavior explicit. An equilibrium prior is learned from inexpensive static equilibrium data and used in a contractive update that continuously pulls predictions toward the equilibrium estimate, improving rollout stability. A lightweight feature-lifted residual model, linear in parameters, learns the remaining one-step mismatch from dynamic trajectory data, recovering transient dynamics. The approach is validated on 200-step simulation rollouts under stronger and faster actuation than in training, with an additional soft-tail hardware test under actuation-frequency shift. The Hybrid method reduces backbone position RMSE by 26% and tip position RMSE by 27%, producing consistent accuracy gains over prior-only and residual-only predictors while remaining stable across all tested trajectories. The same proposed model also improves robustness on standard nonlinear benchmarks against a combined Koopman baseline under matched evaluation protocols.

Conventional flow-induced energy harvesters often rely on idealized NACA foils or simplified shapes that omit key morphological features of natural swimmers—such as curvature, camber variation, and tapering—that govern vortex capture and pressure recovery. Recognizing the performance advantages embedded in these biological traits and building on vortex-exploitation strategies observed in Kármán gaiting, this study develops a koi-carp-derived flexible hydrofoil and systematically optimizes its geometry for bio-inspired flow-energy harvesting. A compact parametric representation of the fish cross-section is formulated, enabling direct geometric manipulation and surrogate-based refinement of the foil’s thickness distribution. Two-way coupled fluid–structure interaction (FSI) simulations evaluate sampled geometries and train a data-driven surrogate model, forming the basis of a multi-objective optimization strategy that enhances synchronization with the unsteady bluff-body wake. FSI comparisons show that the real fish foil outperforms canonical NACA profiles by up to 157% in harvested mechanical power, while the optimized hydrofoil achieves a further 122% increase. Fabricated foils were tested in a controlled water channel, where the optimized configuration delivered up to 30% higher electrical output with reduced numerical drag. A four-foil hydroelastic cascade harvester (HCH) deployed downstream of a bluff body produced a cumulative output of 2.34 μW and a peak single-foil power of 0.713 μW. Field deployment in a natural stream generated 3.82 mJ of electrical energy over 1 hour under low-velocity conditions, confirming stable passive operation. These results demonstrate that biologically derived geometry and surrogate-based optimization enable compact, fully passive hydroelastic harvesters for low-power underwater sensing and distributed flow-energy conversion.

Swimming in fish arises from tightly integrated neural, muscular, skeletal, and hydrodynamic processes that are difficult to capture in compact, transferable models for robotics. We present an interpretable SySID approach that bidirectionally maps between EMG and kinematics in freely swimming koi, further testing its generalization to a robotic fish. Synchronized EMG and kinematics were collected across laminar, Kármán vortex, and reverse Kármán vortex flows spanning 0.146–0.274 m/s. A linear ARX model architecture was chosen to capture both feedforward (EMG to kinematics) and feedback (kinematics to EMG) pathways, enabling the extraction of key system parameters, such as natural frequency, damping ratio, and input–output delays. Cross-individual validation demonstrated robust performance and identified the best-performing fish-trained model, which was then evaluated for cross-domain transfer by replacing EMG input with processed PWM actuation signals from a robotic fish in laminar flow. Despite differences in mechanics and actuation physics, predictions closely matched measured trajectories (mean R² = 0.86 ± 0.13), substantially outperforming a DNN (97.8% higher PFI) trained on the same biological datasets. These findings demonstrate that compact, interpretable SySID models can achieve accurate bio-to-robot transfer, eliminating the need for robot-specific retraining and enabling robotic motion models to be grounded directly in biological function rather than imitation.

This article, which is an extension of the previous work of the authors (Tanveer and Ahmad (2022)) on yaw dynamics, investigates the modeling and control of heave degree-of-freedom of a compact custom designed ROV. Wherein, nonlinear data-driven modeling strategy is adopted to develop a high-fidelity heave dynamic model. The proposed modeling approach uses open-loop real-time experimental data to derive a high-fidelity NARX model of the vehicle. The resulting model accommodates the dynamics of the system in addition to the tether dynamics. The advantage of this approach is its ability to eliminate the need for intricate controller tuning. The identified model consistently demonstrated fitness scores ranging from 82% to 92% in both self-validation and cross-validation tests conducted on distinct datasets. This relative advantage is exemplified in real-time through the testing of a Genetic Algorithm Proportional-Integral (GAPI) controller. The performance of GAPI is subsequently compared with the relatively recent Marine Predators Algorithm (MPA) and the more conventional root-locus tuned PI controllers. The experimental results demonstrate that GAPI provides the most favorable response, achieving a 35%, 76%, and 44% improvement in rise time, percent overshoot and peak time, respectively. Furthermore, the controller effort required by GAPI running on an ATmega328 chipset is 22% less than its counterparts.