Apple's research team published the paper "Perceptive Humanoid Motion from Simulation" on arXiv, unveiling HALO, an autonomous control system for humanoid robots, and simultaneously open-sourcing the training and deployment code.
The authors release the FHNW Muttenz dataset, covering a contiguous 10 km street network and two mobile mapping campaigns about 1.5 years apart, with ground-truth poses accurate to 6-9 mm in position and orientation error below 0.1°. Using this dataset, they systematically evaluate sparse-feature visual localization; with daytime imagery and pre-calibrated cameras, median translation error is 1-5 cm and rotation error is 0.03-0.1°. The authors note that, provided the scene representation is precisely georeferenced, visual localization can approach survey-grade GNSS positioning accuracy and additionally provides full orientation information.
The authors propose the first mmWave radar-based onboard perception-and-control dynamic obstacle avoidance system for small quadrotor UAVs. The system combines a lightweight interacting multiple models (IMM) tracker with a control barrier function (CBF) controller that directly outputs evasive accelerations, and derives sufficient avoidance conditions relating sensing range, relative speed, and control delay.
NoContactNoWorries proposes a Transformer-based multimodal framework that fuses RGB-D vision with robot proprioception to infer binary contact states for hand-object interaction as a pseudo-tactile signal. The authors train a single contact prediction model on multiple objects and verify that this inferred signal can support downstream reinforcement learning agents in completing in-hand object reorientation, and that it generalizes to new objects. Both simulation and real-robot experiments validate the feasibility of inferring contact from vision and proprioception. The paper has been accepted to IROS 2026.
The authors propose SGM-SLAM, a distributed SLAM framework for multi-robot collaboration in GPS-denied, communication-constrained environments, where robots can each initialize their coordinate frames independently and share only limited spatial overlap. The method uses fused RGB-LiDAR point clouds to build a scene graph containing a semantically segmented point cloud layer and a discrete bounded object layer, and performs collaborative matching by exchanging and matching object data with neighboring robots, using multi-step data exchange and optimization to improve communication efficiency. The authors validated effectiveness and communication efficiency on real-world datasets containing limited trajectory overlap, viewpoint variation, repeated structures, and degraded visual conditions.
MosaicIMU is a carrier-conditioned Mixture-of-Experts (MoE) pretraining and adaptation framework for generalizable neural inertial odometry. It composes carrier-specific expert features through a prototype-based router, decodes local velocity and uncertainty constraints, and integrates them with a history-aware EKF. For unseen domains, it freezes the pretrained base model and learns a lightweight expert residual branch; for edge deployment, it reuses the router to select online samples for incremental updates.
The authors propose GELS, a gradiometer-based electromagnetic localization system that uses a compact magnetometer array as an embedded quasi-gradiometer to estimate the local magnetic field and gradient tensor, then maps displacements via the Euler homogeneous relation and uses Procrustes registration with at least three noncollinear sources to recover the array's orientation and position. The closed-form algorithm requires only known source positions and array geometry, with no pre-calibrated workspace field maps, initial pose guesses, or calibrated source magnetic moments; in benchtop experiments, the solver's median runtime was 172.00 microseconds. Perturbation analysis identifies inter-sensor inconsistency and dipole model mismatch as the main accuracy limits.
The authors propose XIT, a sampling-based planner that formulates active gas distribution mapping (GDM) as a next-best-trajectory informative path planning problem, growing a single shared tree toward multiple frontier goals while taking informative gas samples along the way.
The authors propose the Seeing What Matters benchmark to evaluate task-conditioned actionable spatial belief in simulated tabletop manipulation, covering 860 frozen evaluation cases across three scenarios—coffee workstation, drawer/cabinet, and microwave—which expand to more than 115,000 evaluation episodes.
The paper proposes a lightweight path-aware frontier re-ranking method for LiDAR UAV autonomous exploration: a lightweight utility function first retains a small top-N set of frontier candidates, then time-bounded RRT* planning estimates their feasible path costs for re-ranking, and the path for the selected frontier is reused for navigation to reduce redundant global planning.
The study deploys a cucumber length-measurement pipeline based on YOLO26n detection, prompt-based segmentation, and medial arc spline estimation to NVIDIA Jetson Orin Nano and Raspberry Pi 4, and compares both against an RTX 3050 Ti workstation.
The research team proposed a two-component optoelectronic soft suction cup designed for kiwifruit that uses optical signals to estimate interaction forces with real fruit within known contact intervals. On fruit not used in training, it achieved grouped cross-validation R²=0.968±0.005 (MAE=0.138 N), with a median per-fruit held-out R² of 0.973 (MAE=0.134 N).
To address the inaccuracy of conventional frequency-domain readout caused by long interconnects and environmental noise in robotic tactile sensing, this study proposes a time-domain optimization readout method that determines resistance values by fitting a time-domain observation model and using the full waveform rather than only spectral amplitudes. In simulations of a 16×16 array, the method reduced the mean readout error by 20% compared with the baseline; validation over 1,000 trials showed reductions of 24.6% in mean error and 77.6% in standard deviation, and the improvement was also confirmed in cross-point array simulations emulating tactile sensor resistance distributions.
The paper formalizes the attribution problem of inconsistencies between scans and models in LiDAR-inertial odometry and BIM fusion as fault identification over three fault classes, and derives a geometric criterion for determining whether attribution is feasible. On cases that are detectable but not attributable in a two-dimensional study, the method based on this criterion had a conditional error rate of 0.83%, compared with 31.67% for a baseline using uncertainty-based abstention; across 5,600 attributable cases, it produced 5,574 unique attributions with no erroneous attributions.
FATHOM proposes a world-model-guided diffusion action-trajectory selection framework for relative tracking of autonomous underwater vehicles (AUVs) under sparse active light markers. The method first fuses marker observations, inertial measurements, action history, and temporal dynamics using a multimodal task-supervised recurrent state-space model to form a predictive tracking belief; a diffusion action prior then generates multiple multi-thruster trajectories, and the best candidate is selected under a receding-horizon objective and continuously updated based on onboard observations.
Apple's research team published the paper "Perceptive Humanoid Motion from Simulation" on arXiv, unveiling HALO, an autonomous humanoid robot control system, and validating it on the Unitree G1.
Why it matters: Apple's HALO splits task orchestration, motion generation, and tracking into three layers, and reports comparative results of 91% in unfamiliar environments and 70% on composite tasks, offering a look at its layered design and data synthesis pipeline.
Amodal3R at ICCV 2025 performs occlusion reasoning and geometry generation directly in 3D latent space, using visible-region masks and occluded-region masks to preserve real observations and infer occluded geometry and appearance.
The Beijing Academy of Artificial Intelligence (BAAI) proposes ArtHOI, which uses video priors to achieve high-precision reconstruction of 4D articulated human-object interaction without paired 3D data. The method targets the human-object interaction reconstruction task, and its core idea is to replace paired 3D data with video priors.
The study proposes SLA, a spatial-language-action model initialized from a pretrained pi05 policy, which jointly optimizes action prediction and the alignment of intermediate visual embeddings with the spatial representations of a frozen 3D perception model during continual pre-training. The team unified heterogeneous robot datasets spanning embodiments, tasks, and scenes, and introduced feature-dependent gates that adaptively aggregate visual embeddings from multiple layers; the teacher model can use partially available depth and camera calibration information. All auxiliary components are used only during training, and the inference architecture remains unchanged.
A team from Xiamen University and Nanyang Technological University proposed RoTA-Bench, which uses interactive 3D-to-2D projection alignment to evaluate whether vision-language models can precisely adjust an object's 3D pose based on visual feedback. The benchmark contains 674 tasks, of which 100 form a frozen test set; models must choose among 24 discrete rotation actions so that the projection reaches an IoU of 0.90 with the target contour.
The Shen Shaojie team at HKUST has proposed RAVEN, a unified active SLAM framework that uses utility vectors to separately quantify exploration efficiency and localization accuracy, selects global tours according to Pareto optimality, and uses a priority parameter λ (0–1) to determine whether to favor exploration or localization.
MIT researchers propose the UQ-DAAAM system, which quantifies a robot's uncertainty about what it sees by comparing multiple descriptions of the same object from different viewpoints, selects additional viewpoints to correct erroneous annotations, and writes the corrections back to memory. The method adds uncertainty quantification to the DAAAM framework, uses heuristic rules to select frames that can reduce uncertainty without rerunning the vision-language model, and then uses a large language model to fuse the multiple descriptions.
GhostTac proposes a contactless attack that exploits the nonlinear rectification and limited-bandwidth amplification effects of electromagnetic interference (EMI) to convert carefully crafted EMI signals into a persistent DC offset, bypassing on-board filtering and causing stable measurement deviations. The authors verified the attack's consistency across 15 tactile sensors of different types on 10 sensor modules and 2 dexterous hands, and demonstrated real-world impact through three case studies: tactile grasping, slip detection, and material classification. For example, it could cause a domestic robot to exert excessive force. The work has been accepted to ACM CCS 2026.
RegimeVGGT proposes a training-free, layer-wise compression method that achieves a 6.7x speedup over the memory-optimized VGGT* with unchanged reconstruction quality. Through spectral analysis, probing, and causal analysis, the authors find that VGGT's shallow layers lack cross-view structure, its middle layers handle cross-view alignment, and its deep layers are redundant for dense geometry, but their cross-frame attention remains critical for pose.
The authors propose Tactus, a textile-integrated sensing glove that provides both capacitive tactile force sensing and IMU-fused pose tracking with a 1.5 mm fingertip stackup thickness, for collecting natural dexterous manipulation demonstration data. At 95% confidence, the glove's minimum detectable force is 0.59 N, 1.6–2.7 times lower than two commercial tactile glove baselines, with cross-subject consistency of 0.87; under the most severe manipulation occlusion, the relative error of fingertip keypoints is 11.0 mm.
The roughly $200 Waveshare RoArm-M2-S four-degree-of-freedom robotic arm, under a fixed overhead camera, uses a YOLO11n-OBB detector, an ArUco reference pose, and a color classifier to perform color sorting of writing utensils without a wrist rotation joint. For utensils deviating more than 45 degrees from the fixed approach direction, corrective sweeps bring them into a graspable pose within at most 4 attempts. In 196 single-utensil trials, 176 (89.8%) landed in the correct color bin; of the 20 failures, 19 were grasp slips or missed grasps and 1 was a color mislabel.
This paper systematically reviews multiple rotation representations of SO(3), including Euler angles, axis-angle vectors, quaternions, rotation matrices, exponential maps, and emerging continuous and probabilistic methods, and compares them across dimensions such as continuity, susceptibility to gimbal lock, computational efficiency, storage requirements, interpolation, and composition operations. Empirical results show that quaternions are advantageous due to their compactness and efficiency, while 6D continuous representations and matrix Fisher distributions offer greater advantages in continuity and uncertainty modeling.
The paper proposes a planner-conditioned air-ground assistance method that evaluates how map uncertainty affects the UGV's current MPPI rollouts. When navigation remains degraded, it re-scores the same rollouts under resolved map hypotheses, selects the map layer whose request yields the largest improvement, requests the corresponding aerial measurement, and fuses it to replan.
This study examines the visual stabilization performance of boundary-layer sliding mode control (SMC) relative to causal baselines such as LPF and PID under plant-binding conditions, where disturbance velocity approaches or exceeds the actuator slew limit and the per-step actuation budget is constrained.
This paper proposes a lightweight reflection-aware front-end for feature-based stereo visual-inertial odometry (VIO) that estimates ground height in real time and rejects only feature candidates whose inferred 3D positions lie below the estimated ground. The method uses a ground-region mask to restrict the validation scope, constructs frame-level ground-height measurements from stereo height uncertainty and pose uncertainty, stabilizes the estimate with a scalar Kalman filter with NIS gating, and performs selective rejection with an uncertainty-aware safety margin.
The authors propose OdorSpaces, a physics-simulation-based platform and benchmark for visual-olfactory embodied navigation. It integrates 3D odor transport and dispersion simulated by Fire Dynamics Simulator (FDS) into Habitat-Sim, enabling agents to navigate realistic indoor environments using both visual and olfactory observations.
At Rogers Dry Lake in Edwards, California, NASA completed simulated lunar descent and landing maneuvers using an Alta-X drone carrying the SPLICE guidance, navigation, and control payload. The SPLICE payload uses its guidance system to map terrain and assess landing zones, redirecting to a safer location when it determines the target area is unsafe, and generates high-resolution digital elevation maps from light detection and sensor data.
D-Robotics, together with the University of Tokyo and other institutions, released the RawVLA technical approach, which adds a learnable neural ISP module before the VLA policy while keeping the VLA model frozen, using action error to train the imaging front end in reverse. On real robots, four dual-arm tasks were tested with π0.5; the average success rate in low light rose from 0% with the default ISP to 66.5%, versus 75.0% in normal light, where the default ISP achieved 76.5%.
Why it matters: The approach brings the imaging front end into the learnable pipeline and provides comparative data under low light and normal light, offering a reference for vision pipeline design.
BSC-Nav is an arXiv paper (2610.02784) aimed at indoor object navigation, long-instruction following, active embodied question answering, and mobile manipulation, addressing the problem that multimodal large models can understand the current view but struggle to support spatial cognition. This analysis article from Guyuehome says it moves embodied intelligence from reacting to a single glance toward retrievable spatial cognition, but currently only the abstract is provided; method details and experimental results are not elaborated.
EvolvingNav proposes a dynamic search framework to address the problem of robots tracking items that may be moved in long-term environments. The framework fuses timestamped 3D observation history and distinguishes three cases: the target remains at its most recent location, the target has moved to a known location, and the target has entered an unknown area.
RPV-SemNav proposes a zero-shot indoor navigation method that requires no prior map. It maps target and observed objects into probability vectors over nine room categories (RPV) and uses spatial co-occurrence semantics to guide exploration. The system combines open-vocabulary detection, CLIP semantic alignment, and free-space propagation, enabling the robot to first understand the room and then decide where to look for the target.
SSTG-Nav proposes a reusable object navigation framework for long-term deployment scenarios, focused on addressing the mismatch between observation poses and docking poses. The framework uses a single task-agnostic RGB-D mapping pass, employing a vision-language model (VLM) for detection and depth back-projection to generate reachable targets. The material provides only an abstract and does not give full experiments or results.
Super Odometry 2.0 introduces a four-layer adaptive mechanism for motion estimation when cameras and LiDAR degrade in scenarios such as darkness, repetitive corridors, and dense smoke. The system filters reliable observations at the feature layer, identifies weakly constrained directions at the direction layer, and dynamically adjusts the factor graph fusion strategy at the engine layer.
The paper LT-Mem from the APRL lab at Daegu Gyeongbuk Institute of Science and Technology (DGIST) in South Korea won the IROS 2026 Best Paper award. The work proposes a volatile-perception spatiotemporal memory framework that uses three memory layers—Live, Delta, and Meta—and three volatility-based update strategies—coverage, retention, and multi-hypothesis—to solve the temporal forgetting problem in which new observations overwrite old memories when a robot revisits the same space multiple times.
G1 Brunson uses event-based rewards and asymmetric actor-critic training, bringing the depth camera directly into the observation loop during training to form a G1 whole-body dribbling policy. Reproducing the official weights locally in MuJoCo gave an average of 43.5 crossovers over 12 episodes with zero falls, matching the official results.