Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2204.13281

Efficient Autonomous Navigation for Terrestrial Insect-Machine Hybrid Systems

Huu Duoc Nguyen·Van Than Dung·Hirotaka Sato·T. Thang Vo-Doan
View original source ↗Read source document ↗Export metadata ↓

Abstract

While bio-inspired and biomimetic systems draw inspiration from living materials, biohybrid systems incorporate them with synthetic devices, allowing the exploitation of both organic and artificial advantages inside a single entity. In the challenging development of centimeter-scaled mobile robots serving unstructured territory navigations, biohybrid systems appear as a potential solution in the forms of terrestrial insect-machine hybrid systems, which are the fusion of living ambulatory insects and miniature electronic devices. Although their maneuver can be deliberately controlled via artificial electrical stimulation, these hybrid systems still inherit the insects' outstanding locomotory skills, orchestrated by a sophisticated central nervous system and various sensory organs, favoring their maneuvers in complex terrains. However, efficient autonomous navigation of these hybrid systems is challenging. The struggle to optimize the stimulation parameters for individual insects limits the reliability and accuracy of navigation control. This study overcomes this problem by implementing a feedback control system with an insight view of tunable navigation control for an insect-machine hybrid system based on a living darkling beetle. Via a thrust controller for acceleration and a proportional controller for turning, the system regulates the stimulation parameters based on the instantaneous status of the hybrid robot. While the system can provide an overall success rate of ~71% for path-following navigations, fine-tuning its control parameters could further improve the outcome's reliability and precision to up to ~94% success rate and ~1/2 body length accuracy, respectively. Such tunable performance of the feedback control system provides flexibility to navigation applications of insect-machine hybrid systems.

Explore related subjects

cs.RO

Keep this discovery

BibTeXRIS

Huu Duoc Nguyen, Van Than Dung, Hirotaka Sato, T. Thang Vo-Doan. 2022-04-28. Efficient Autonomous Navigation for Terrestrial Insect-Machine Hybrid Systems. https://doi.org/10.1016/j.snb.2022.132988

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in $\pi_{0.5}$. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to $\pi_{0.5}$, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains $\pi_{0.5}$'s robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming $\pi_{0.5}$ on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

cs.RO↗
arXiv2026

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

Imitation learning has achieved impressive results in robotic manipulation, yet most existing approaches assume clean backgrounds and lack explicit mechanisms for obstacle-aware motion generation. Extending such policies to cluttered, real-world scenes with unstructured obstacles remains a key generalization challenge. We present ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder. ObstaDiff extracts a structured target-obstacle-background representation, enabling the downstream alignment policy to generate end-effector trajectories toward a target-centered bottleneck pose while reasoning about surrounding obstacles. We evaluate ObstaDiff on 61 real-robot greenhouse trials per method (366 executions in total). ObstaDiff achieves 75.41% average task success and 8.20% average obstacle collision rate, outperforming representative imitation-learning baselines and improving generalization in cluttered agricultural scenes.

cs.RO↗
arXiv2026

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.

cs.RO↗