Skin lesion segmentation supports computer-aided dermatology, but blurred boundaries, low contrast, and marked variation in dermoscopic appearance make reliable delineation difficult. Foundation models such as the Segment Anything Model (SAM) offer strong visual priors, although their sensitivity to prompt quality limits their reliability in few-shot medical settings. We present PADS, a novel perturbation-aware distillation framework for robust skin lesion segmentation under prompt variability. During training, we perturb bounding-box prompts derived from ground-truth masks to simulate realistic prompt noise. A lightweight relevance module then estimates channel-wise feature importance under these perturbations and guides selective distillation from MedSAM into a compact UNet. This training improves robustness to imperfect or noisy prompts, allowing pseudo-prompts to support reliable segmentation. At inference, the UNet either produces the segmentation directly or supplies a pseudo-prompt for optional MedSAM refinement. Experiments on ISIC 2018 and cross-dataset evaluation on PH2 show improved few-shot segmentation accuracy and slower performance degradation as prompt perturbation increases, compared with standard distillation. PADS adds only limited computational overhead relative to MedSAM. The experimental results support perturbation-aware distillation as a practical approach to robust few-shot medical image segmentation.

Light Detection and Ranging (LiDAR)–Inertial Odometry (LIO), which tightly fuses complementary data from LiDAR and Inertial Measurement Units (IMUs), is a key technology for high-precision state estimation in legged robot navigation. However, conventional Iterative Closest Point (ICP)-based LIO  frameworks provide only pose constraints. Their position estimates often exhibit centimetre-level jitter due to LiDAR measurement noise, especially when the robot is stationary or moving slowly. This temporal inconsistency degrades the performance of downstream perception-driven motion planning and control.  In this paper, we propose LiDAR–Inertial–Joint Odometry (LIJO), a novel state estimation framework for quadruped robots that integrates LiDAR, IMU, and joint encoder measurements within a manifold extended Kalman filter (EKF). The torso velocity is first estimated from joint angles and angular velocities via forward kinematics and is then used as a proprioceptive velocity factor in the EKF prediction step.  To cope with foot slippage and aggressive motions, we further design a dynamic weighting scheme that adaptively adjusts the confidence of the joint-based velocity factor according to the current motion speed,  while treating IMU measurements as filter observations rather than inputs. The resulting system maintains the localization accuracy of state-of-the-art LIO methods and significantly suppresses high-frequency jitter in the estimated trajectory. Extensive experiments on a real quadruped robot in challenging outdoor scenarios, including steep staircases and large-scale loop trajectories, show that LIJO produces smoother and more stable odometry than existing LIO and kinematic-inertial baselines, while preserving real-time performance. The proposed approach thus provides more reliable state inputs for perception and control modules in all-terrain legged locomotion.

Recent advances in legged robots have substantially improved their locomotion capabilities over outdoor and complex terrains. However, quiet locomotion for humanoid robots in noise-sensitive indoor environments remains underexplored, despite its growing importance in human-centered applications.  While encouraging progress has been made in quadrupedal robots, transferring the quiet locomotion ability to humanoid robots remains nontrivial due to their fundamentally different foot-ground contact patterns. This paper proposes a control method for reducing foot–ground contact noise during humanoid walking, achieving compliant contact and continuous regulation of locomotion noise by establishing a foot corner contact model along with a virtual compliance parameter. The experimental results show that the average sound pressure level is reduced by 4.88 dB.