A study published in the International Journal of Systems, Control and Communications proposes combining fuzzy logic with a self-coupling PID controller for multi-drone formation control.
The authors propose RynnUnify, a 16B unified embodied model that combines embodied understanding with long-horizon visual planning through video-language interleaved reasoning. The model covers spatial reasoning, physical prediction, and grounding capabilities, linking physical world understanding with visual anticipation across subtasks. The post also provides links to the code and paper.
On October 26, the qualifying round of the first CMG World Robot Mount Tai Climbing Competition started on the trail from Red Gate to Zhongtian Gate in Mount Tai, with multiple domestic teams fielding legged and wheel-legged composite robots. The course is about 3.8 kilometers long with more than 3,100 steps. Rain during the race made the stone steps slippery, testing the robots' balance control, perception and decision-making, and battery life in a real mountain environment. One robot from Dongtai Technology completed the speed race in about 58 minutes with about 80% battery remaining. The event also includes a loaded-carrying race for legged robots, simulating mountain emergency supply delivery scenarios.
KUKA Mobile Robotics will exhibit the KMP L series latent lifting mobile robots, a one-stop pallet handling solution, and the KUKA.AMR software 3.0 platform at CeMAT ASIA in Shanghai from November 3-6, 2026; together, the three form the warehousing and logistics implementation of the "KAI" intelligent platform. The booth will also demonstrate a full-scenario, multi-system collaborative operation loop covering receiving and inbound storage, material transfer, high-bay storage, and sorting and outbound.
The JAKA Kargo wheeled humanoid robot, running the JAKA EVO embodied intelligence operating system, has been deployed for bin handling at the headlight plant and electronics plant of a leading Chinese auto parts manufacturer. Per-bin handling time dropped from 105 seconds per bin to 28 seconds per bin, nearly a 4x efficiency gain, and the robot also stacks bins five layers high and recovers empty bins by layer.
The author ran 18 experiments comparing the TEB and DWA planners in a Gazebo mecanum-wheel robot simulation, with the title stating a 1.65x difference between them. The author also notes that when the planners moved sideways throughout, their lateral-movement rates differed by 100x, yet this was completely invisible on the trajectory plots.
The authors propose GARV, which combines graph-based action contracts with a safety monitor to produce a model-relative safety certificate or counterexample for high-level actions such as goto(region), and to provide a minimum-cost safe refinement when alternative routes are available.
Goal2Pixel proposes a pure pixel paradigm that reformulates vision-and-language navigation in continuous environments (VLN-CE) as navigable pixel grounding: the model predicts navigable pixels on the image plane, which are then back-projected into 3D waypoints for forward movement, while turning and stopping are encoded by auxiliary left, right, and bottom regions.
The paper proposes a legal planning stack that uses Defeasible Deontic Logic (DDL) to constrain a motion planner, leveraging a learned world model for planning and to supply legal context, thereby enabling ex ante intervention before an illegal action is executed. The stack was deployed in a scenario where a simulated robotic arm pushes blocks on a 3x3 grid. Results show that the legally constrained agent complied with norms at a markedly higher rate than the unconstrained one, and that modeling perceptual uncertainty further raised the compliance rate; legal reasoning ran efficiently at runtime, its rulings were auditable, and the stack adapted to exogenous signals and endogenous rule changes.
The authors propose a grid-based spatio-temporal Gaussian process-Kalman filter framework for learning-based multi-robot informative path planning, representing anonymous target presence as a single latent variable field over a discrete workspace grid rather than maintaining one Gaussian process per target.
The study proposes a language-driven navigation framework that enables mobile robots to understand natural-language requests such as "go to the mailbox," identify the referenced object, estimate its position using RGB-D data, and generate a navigation goal that is then executed by the ROS 2 Nav2 navigation stack.
The authors propose GTP-FA, a two-stage "grasp-then-plan" framework for robotic manipulation: it first generates grasp candidates, then performs downstream motion planning conditioned on the selected grasp. The framework learns a failure attribution model that outputs a distribution over failure modes for failed trajectories, and uses it to separately optimize the grasp scoring and planning modules. Simulation and real-robot experiments show that GTP-FA improves overall task success rates over baselines including RL, IL, diffusion policies, and VLA, and the paper has been accepted to NeurIPS 2026.
The paper studies the Hamiltonian Path Problem with Probabilistic Terminals (HPP-PT), whose goal is for a mobile robot to visit all candidate locations to find a target while minimizing expected path cost. The authors propose RPT*, a search method with optimality guarantees that uses dynamic programming in a new state space to bypass history dependency, along with a heuristic to speed up computation. The RPT*-based HATS system, combined with Bayesian filtering or autonomous exploration, found targets faster than baseline methods on average in both simulation and real-robot experiments.
The authors propose a semantic-geometric graph task representation that jointly encodes object identities, inter-object semantic relations, and each object's motion history, consisting of an MPNN encoder and a Transformer decoder; the encoder processes only the temporal scene graph and produces structured representations decoupled from action labels.
The authors propose an analytic event simulator that synthesizes event streams directly from scene geometry and ego-motion without image rendering, generating 64x64 event observations in just 17 microseconds on a single GPU, over 400 times faster than state-of-the-art rendering pipelines. Reinforcement learning training for an event-camera obstacle-avoidance policy based on this simulator converges in under 30 minutes, three orders of magnitude faster than training on rendered events, and transfers zero-shot to ray-traced event simulation in Isaac Sim.
Why it matters: This work uses analytic event simulation to bypass image rendering, cutting event-camera reinforcement learning training time to under 30 minutes, and completes real-world deployment on a 56-gram drone.
KEPT proposes a navigation method for enclosed spaces such as tunnels and mines, using conformal prediction to calibrate keepouts around mapped walls under degraded sensing, and adjusting the margin according to a label-free degradation severity estimate to maintain coverage. The planning and control layer enforces a braking-distance condition on the keepout at plan time and on every command, using the measured tracking residual as its only margin and never altering the keepout.
The authors propose Local Spatial Matrix Memory (LSMM) based on Hadamard memory, which lets reinforcement learning agents store task-relevant information in position-based memory cells. On an autonomous maze exploration task, LSMM's maze coverage is comparable to strong recurrent networks and finite-history baselines, and it is the only architecture that remembers the maze layout, reducing reconstruction error to one third. The work targets the problem that humanoid and legged robots in complex environments need to remember information long after it leaves their field of view before it is used.
RAVEN is an active SLAM framework for quadrotors that unifies planning of exploration and active loop closure under localization uncertainty, and uses a priority parameter from 0 to 1 to adjust the emphasis between exploration efficiency and localization accuracy. The framework first identifies frontiers and active loop closure candidates and generates global tour plans, then evaluates them with a utility vector, and finally a perception-aware navigation planner generates smooth trajectories based on an online Fisher information field to reduce visual state estimation error.
The authors propose Omni-IGN, a fully onboard drone image-goal navigation (ImageNav) system that integrates quad-fisheye perception, an attention-based reinforcement learning policy, and a collision-aware safety layer. The policy adaptively fuses goal-relevant features across multiple views to provide directional guidance for continuous navigation, and the quad-fisheye RGB images support both ImageNav and obstacle avoidance without a dedicated depth sensor.
An arXiv paper proposes modeling bio-inspired magnetic navigation (BIMN) as a gradient flow control and guidance problem, using magnetic inclination and intensity of Earth's magnetic field to guide a system through intermediate waypoints to a destination within a predefined region. The authors note that magnetic coordinates do not map one-to-one to geographic locations and are ambiguous, but that gradient flow can act as a "water current" carrying the system's motion and be steered. The framework could be used in engineering to build geomagnetic navigation infrastructure and to define and follow prescribed routes, and also to analyze animal migration routes that rely on magnetoreception.
The paper proposes a method for enabling two personal mobility vehicles (PMVs) to drive autonomously side by side: after a global path is given, each vehicle runs its own sampling-based model-predictive planner, the two exchange only the odometry information each can observe of the other, and a common rule is used to make a joint decision on a utility matrix over pairs of candidate trajectories.
REACH is an RL-based hierarchical framework that enables a Unitree G1 humanoid robot to traverse height-constrained environments through variable-height bipedal walking and crawling. Its policies regulate body height over complementary command ranges: 1.27–0.50m for bipedal walking and 0.50–0.20m for crawling, and a bidirectional transition policy connects crouched walking and crawling. The framework also combines a LiDAR planner that converts point clouds into collision-free three-dimensional paths and locomotion commands. Real-world experiments validated height and speed tracking, terrain traversal, mode switching, and confined-space traversal; the code and videos have been released.
For multiple observations under image-quality constraints in drone-based 3D reconstruction and inspection, where overlap-based planning heuristics cannot guarantee such observations, this work models GSD-constrained k-coverage viewpoint selection as a set multi-cover problem. Candidate viewpoints are generated along outward surface normals, screened by distance, viewing angle, field of view, and occlusion, and then a dynamically weighted greedy heuristic prioritizes coverage gaps and scarce viewing angles. Across two structures, four voxel resolutions, and three coverage requirements, the method achieves full or near-full k-coverage, using only 3.00%–16.39% more viewpoints than ILP.
The authors propose SG^2SLAM, a 3D Gaussian Splatting SLAM method for monocular outdoor navigation that replaces per-frame cross-dimensional correspondence with a chunk-level metric prior, so that tracking and mapping share the same geometric source. The method also introduces a ray-conditioned 3DGS kernel that extends each primitive with a viewing-direction subspace, and jointly optimizes spatial geometry and poses. On the KITTI and Waymo Open datasets, SG^2SLAM outperforms per-frame association baselines in the monocular outdoor navigation task. Code will be made publicly available upon acceptance.
ASPEN is an event-triggered scheduler based on command persistence prediction, designed to reduce repeated semantic reasoning calls in navigation VLA policies. On frozen NaVILA in the cross-dataset RxR-CE val-unseen evaluation, ASPEN reduces VLA calls by 9.5% and estimated inference time by 8.1% (including scheduling overhead), while preserving action sequences identical to the baseline in 92.1% of episodes.
cuArms is a conflict-based planner co-designed with GPU parallelism. It decomposes the search space using reusable multi-modal roadmaps and resolves conflicts and deadlocks through lazy search. It integrates with a high-level scheduler to jointly optimize task assignment, scheduling, motion, and manipulation skills. Experiments report real-time initial solutions and anytime improvements in motion quality and scheduling, without domain training for learning-based methods. The authors say it provides demo videos on both simulated and real industrial tasks.
San Francisco-based Bedrock Robotics announced the completion of a $600 million Series C funding round, co-led by Alphabet's growth fund CapitalG and Emergence Capital, with participation from Temasek, Nvidia, Bessemer and others. The post-money valuation is $4.1 billion.
Hikrobot has officially launched its "Mingzhi" series of standalone intelligent products, integrating perception, decision-making, and execution into the robot body itself, eliminating reliance on a scheduling architecture so that a single unit can complete the entire material-handling workflow. The series debuts with two products: the Z1-300 underride transport robot and the Z2-1500 forklift transport robot. The company says unboxing, mapping, and task dispatch can be completed in as little as 30 minutes, and a single map can cover up to 200,000 square meters.
Damon Technology will hold the GPC 2026 Global Partner Conference on November 6-7 at its Damon Science and Innovation headquarters in Huzhou. Live on-site demonstrations will show four warehouse workstation solutions validated through internal POC, including intelligent parcel feeding for cross-belt sorters, feeding for the Flying Shuttle intelligent sorting robot, production line-side handling, and warehouse depalletizing and palletizing handling, with humanoid robots working in coordination with sorting hosts, conveyors, and shelf pallets.
According to statistics from the Mobile Robot Industry Alliance, as of October 26, 2026, 14 acquisitions or mergers had occurred in the mobile robot sector, covering key technologies, complete machines, software systems, and mature businesses. The article groups these deals into three categories: filling technology gaps, entering new use cases, and completing the warehouse operation chain, and argues that industry competition is shifting from individual product capabilities to key control points within complete systems.
Researchers from UIUC, Google, Stanford, UC Berkeley and CMU jointly published the review "Proactive AI for Superintelligent Agents," systematically mapping the research landscape of proactive AI and proposing a 6A framework composed of six capabilities: Awareness, Anticipation, Agenda, Arbitration, Action and Adaptation.
FastHarness is an experience-driven robot execution framework that uses π0.5 to generate actions and GPT-6 Astra to review and correct them, adjusting the review interval according to task stage and past review results. Across four simulated manipulation tasks in RoboDojo, it achieved an average success rate of 97.19%, higher than the 80% reported for π0.5 + GPT-6 Astra in the GPT-as-Policy report.
Embotech and BMW announced that they have completed the movement of 1 million vehicles using autonomous driving technology at four plants in the UK and Germany, averaging about 3,500 moves per day with availability exceeding 99.5%. Their Automated Driving In-Plant solution places perception, including Hesai lidar, on the production line infrastructure side, so vehicles need no additional sensors, and it is paired with a deterministic safety architecture independently certified by TÜV SÜD.
Xpanner has launched the X1 Piling R6 fully autonomous pile-driving robot, designed to install posts autonomously at utility-scale solar and battery storage sites under the supervision of a single operator. The system is built on the Everstar R6 tracked chassis and uses high-precision GNSS and onboard sensors to navigate autonomously to pile locations. It can drive piles up to 23 feet (7.0 meters) long to a maximum driving depth of 15.7 feet (4.8 meters), and is equipped with a 97 kW engine and a hydraulic hammer with up to 1,260 J of impact energy.
The authors propose an inspection planning framework that replaces geometric visibility checks with a learned camera information metric based on a classifier variational autoencoder (VAE), to address inspection failures caused by drastic orbital illumination changes. The method implements a guidance, navigation, and control architecture in a photorealistic physics simulator and tests multiple orbital illumination conditions and viewpoints: average brightness reaches 0.57, with 81.6% of observations above 0.25, compared with 0.02 (3.0%) for geometric planning with illumination bands and 0.04 (6.0%) for pure geometric planning.
The paper proposes a path-tracking algorithm for articulated vehicles with a single trailer. It applies a lateral control law at the trailer level and makes short-horizon predictive adjustments to the tractor steering angle, so that both forward and reverse motion converge stably to the target path. The method is geometry-based and requires no per-vehicle calibration or training. In a high-fidelity physics simulation, the steady-state or final lateral error on straight-line, circular-arc, and reverse docking trajectories was 0.02–0.05 m. The authors tested it on a small-scale tractor-trailer robot, with the controller running on a low-cost microcontroller; under about 200 ms of pose-detection latency, the lateral error in repeated reverse docking was below 13 mm.
The authors propose VLN on the Fly, an onboard vision-language navigation stack that keeps instruction grounding, planning, and control as separately inspectable stages: a quantized VLM grounds the instruction to a coarse image cell, depth lifts it to a 3D goal, a fast B-spline planner generates a feasible trajectory, and a pretrained reinforcement learning policy tracks the trajectory and outputs motor commands across multiple quadrotors.
The SHRIMP system lets users automatically generate hierarchical robot primitive plans using natural language, and iteratively revise those plans through re-prompting and explicit correction. After each revision, users can validate the plan in simulation and, once satisfied, execute it on the physical robot. A user study with 35 participants on tabletop kitchen task planning showed that SHRIMP improved users' perceived control and robot transparency.
This study proposes a spatiotemporal informative planning method based on model predictive path integral (MPPI) control for unmanned surface vehicles (ASVs) to search for and capture multiple drifting targets. The planner couples target drift prediction with exploration objectives through a cost design, optimizes continuous trajectories over long horizons, and directly generates kinematic commands; in the interception stage, pure pursuit guidance is used to achieve physical capture. In simulation, the method captured 18% more targets than the strongest baseline, and the approach was validated in real-boat trials.
The authors propose PRISM, which trains a lightweight action head on features from a frozen latent world model encoder to obtain a goal-conditioned action prior, then uses its mean and predicted uncertainty to guide action search, with the world model evaluating the consequences of actions. Experiments on four simulated control tasks and two real-robot platforms show that the lightweight action head improves planning performance, and that the same fusion interface can accept a diffusion prior over the same frozen features without modification.