The paper proposes Future-Window Inverse Kinematics (FWIK), an online inverse kinematics selection method that considers several future waypoints, connects multiple IK candidates in a layered joint-space graph, ranks them with a motion-time estimate, and then uses a learned model to remove transition paths prone to self-collision.
The author examines the applicability of RRT* to triangle-mesh terrain, noting that the original RRT* cannot run directly on a mesh because the surface has zero volume, so uniform sampling never hits it. The proposed Mesh RRT* solved every run on terrain with slopes up to 75 degrees, but its cost function is biased: after 30,000 iterations the reported cost is on average up to 2.7% below the exact geodesic, and the returned path is on average 0.1-0.5% longer.
ZipDrift proposes using a one-step drifting generator to learn cost corrections for short-horizon MPC, trained only on cost evaluations of candidate corrections without backpropagating through the optimizer.
The authors propose a multi-robot closed-loop adaptive sampling framework in which a single learned generative model performs forecasting, uncertainty estimation, planning, and measurement assimilation simultaneously. The model generates ensemble forecasts in latent space and decodes them into physical ocean states, uses ensemble statistics to construct A- or D-optimal sampling objectives, selects sampling locations within the robot-reachable range constrained by predicted currents, and feeds measurements back into the latent state through observation-conditioned diffusion sampling.
This paper proposes a contact-implicit whole-body optimization framework for humanoid robots to generate dynamic motion trajectories on parameterizable complex terrains such as steps and ramps, without requiring a predefined contact sequence. The method approximates ground geometry with smooth surfaces and extends rigid-body interaction from planar surfaces to arbitrary smooth surfaces through new contact constraints, using nonlinear programming to plan motions across various terrain topologies. The authors conducted preliminary feasibility tests on non-coplanar terrains in simulation and on the real robot ErgoCub.
REEMAN uses unmanned forklifts such as the Ironhide 3.0 to explain that AMR forklifts suit repetitive, long-distance, multi-shift pallet routes in heavy manufacturing. At a new energy factory in Huzhou, one Ironhide 3.0 completes about 160–200 transport trips per day on a route of about 47 meters.
Boston Dynamics has released Stretch Gen 2, its second-generation autonomous mobile unloading robot, with hardware and structural upgrades based on first-generation deployment data and more than 100,000 hours of operating data. The new machine reduces internal cabling by 81%, uses automotive-grade connectors, joints that can rotate continuously more than 360°, and an upgraded gripper. It can unload up to 1,000 boxes per hour, its battery can support two shifts, and fast charging takes about 75 minutes to 90%.
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.
GlobalLogic's Silicon & Embedded division partnered with Haystack Robotics to design an autonomous mobile robot (AMR) from the concept stage, combining real-time perception, edge intelligence, and navigation to perform hospital-grade UV disinfection with as little manual intervention as possible. The robot offers two modes, autonomous navigation and "follow me"; the platform separates the mobile chassis from the UV payload so other modules can be swapped in later, and it reuses components such as ROS and sensor fusion.
Deep Blue AI's "Algorithm Explained" column published an article explaining the two sampling-based planning algorithms RRT and RRT*: RRT uses random sampling, finding the nearest node, expanding toward the sampled direction, and collision detection to grow a tree from the start toward the goal, addressing the difficulty of enumerating high-dimensional configuration spaces in advance.
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.
Automation should not stop at the building entrance. A Sherpa 10K #AMR carries a fully loaded cart across the yard, turns in, and passes through a rolling shutter door. From outdoor to indoor, all dispatched as one unified system.
From a supplier perspective, REEMAN provides a five-item checklist of mechanical prerequisites, communication architecture, and responsibility division for autonomous forklift and elevator integration. For a single elevator, a local LoRa direct connection to the elevator control module is used; for multiple elevators, MQTT is used with the fleet system queuing and dispatching. The elevator control module only coordinates calls and status and does not replace the elevator's native safety controls. In the Maoming factory case, Ironhide transports about 1,000 kg of wire rod per trip over a one-way distance of about 100 m, completing 65–85 cross-floor elevator tasks per day.
At CeMAT ASIA 2026, Seer Robotics exhibited its Robot Brain product line and several robots equipped with the platform, including the X1 PRO humanoid robot autonomously completing a water-fetching task, the P300 and P1500 AI delivery robots collaboratively avoiding obstacles, and an omnidirectional stacker forklift autonomously identifying and picking up various pallets. Robot Brain consists of three parts: Model, Cerebellum, and Neural pathways. It has been adapted to more than 400 types of core components and supports more than 2000 robot SKUs.
An IROS 2026 plenary session focused on space robotics, with experts from NASA, JAXA and academia discussing the roles of robots in lunar exploration, human spaceflight and in-orbit operations. After pausing the Gateway program, NASA shifted to the MoonBase project, with an initial operating capability targeted for 2029; robots will be needed to build modules, transport supplies and enable in-situ resource utilization. JAXA's MMX mission sampling robot needs to collect more than 10 grams of regolith in under a minute.
The Ruiman Wind Fire Wheel (WBOT11B) chassis has an open-source SDK and API, and can be used for mobile robot algorithm validation in university laboratories and MVP development of commercial service robots for enterprises, eliminating the work of building low-level drivers and motion control from scratch. This content takes ROS secondary development and navigation deployment as its thread and provides a deployment guide for the above scenarios.
Huaner Technology compares three entry-level robot cars: miniAuto Pro, TurboPi, and ClawPi. The miniAuto Pro is based on ESP32 and supports Scratch and Arduino.
The first CMG World Robot Mount Tai Climbing Competition concluded on the course from Hongmen to Zhongtianmen in Tai'an, Shandong. The Unitree A2 robot dog won the legged robot sprint with a time of 43 minutes 41 seconds (actual 41 minutes 41 seconds plus a 2-minute penalty), using fully autonomous mode throughout to perceive and make decisions in real time on irregular stone steps.
Liu Shilong, a postdoctoral researcher at Princeton (joining Columbia University in fall 2027 as a tenure-track assistant professor), has shifted his research focus to self-evolving agents, with robotics and scientific discovery as application scenarios. He is a core author of the open-world detection model Grounding DINO, which has over 2 million monthly downloads on Hugging Face, and whose open-source project has accumulated over 30,000 GitHub stars.
At CeMAT Asia, which opened on November 3, Ingsmart exhibited the Messol embodied-intelligence loading and unloading robot solution, designed for native mixed-box conditions inside truck trailers; it supports grasping of mixed boxes in multiple box types and orientations, and the operation process requires no manual entry into the trailer for sorting.
Starting at 10:00 on November 2, six AgiBot Genie G2 humanoid robots worked 24 consecutive hours at a normally operating convenience store in Xuhui, Shanghai. They were assessed against store standards including on-duty time, task success rate, and response time. In the end, 4 passed probation, while Lengjie and Juanwang did not yet pass probation due to shortcomings in on-duty initiative and job stability.
Starting November 2, six Genie G2 robots equipped with AgiBot's Genie Master embodied Agent framework worked continuous 24-hour shifts in a real convenience store. In the end, four passed the probation assessment, completing a cumulative 1,730 tasks, including greeting customers 683 times, fetching and delivering 369 items, and making coffee 147 times.
PHYMI released its first Physical Agent action partner, Sagi, on October 28. It uses a four-wheeled legged configuration with a humanoid upper body and a companion cargo box, and is positioned to complete long-range mobility and object manipulation in open, dynamic real-world scenarios.
Yobotics' "Xingzhe Taishan" humanoid robot fully autonomously traversed more than 3,100 stone steps on Mount Tai at the first CMG World Robot Mount Tai Climbing Competition, relying on its own perception and decision-making systems. The robot is equipped with multimodal perception, autonomously identifies step edges and obstacles, builds a map of the mountain path and plans its route, and then dynamically adjusts stride length, step height and landing posture through its self-developed joint modules and motion-control cerebellum. The team said the competition was a real-world validation of its full-stack self-development approach, and that it will next advance deployment in scenarios such as mountain inspection and emergency rescue.
After merging with ATOMIX, Force Machine made its debut at CeMAT ASIA 2026 with a robot multi-agent tiered operation system that divides case-piece picking into three tiers by difficulty: economical robotic arms handle about 60% of standard goods, embodied robots handle about 20% of irregular, hard-to-grasp goods, and the remaining 20% of long-tail tasks are covered by human workers.
Ruoyu Technology exhibited independently for the first time at ROBOTECH2026, held October 27–29 at the Shenzhen World Exhibition & Convention Center. Together with Geely Auto and Zhengxing Technology, it recreated a smart refueling worksite at 1:1 scale, where the Ruoyu Lanyue robot autonomously completed the entire process—taking up the nozzle, opening the fuel tank cap, inserting the nozzle to refuel, and returning the nozzle to its place—without any manual intervention.
XPENG ROBOTICS proposes the embodied vision-language model Capek 0.5, training separate experts for four execution capability categories—spatial reasoning, temporal understanding, action guidance, and state verification—then integrating them into a single model via TIES merging and routed MOPD distillation.
WAM trains a forward-dynamics world model on quadruped robot locomotion data collected under convex model predictive control, replaces hand-crafted steering laws with receding-horizon sampling planning, and combines A* global paths with dynamic obstacle extrapolation to achieve navigation and obstacle avoidance. The material states that all numerical values come from local reproduction experiments.
36Kr has learned that Shenzhen Yicheng Autonomous Driving Technology Co., Ltd. (Yicheng Innovation) recently closed a RMB 200 million Series C round. Investors include Yueke Group, Shanda Investment, Anhui Guotou, and Foshan Venture Capital. The funds will be used for factory capacity upgrades, core technology iteration, and commercialization deployment.
On October 26, the qualifier of the first CMG World Robot Mount Tai Climbing Competition started on the trail from Tai Shan's Red Gate to the Mid-Heaven Gate, with multiple domestic teams fielding legged and wheel-legged hybrid robots. The course runs about 3.8 km and includes more than 3,100 steps. Rain fell during the competition, and the slippery stone steps tested the robots' balance control, perception and decision-making, and endurance. The event also features a legged-robot load-carrying race and an all-terrain mobility pathfinding challenge. Zhishen Technology's "Tongchui M1" has a maximum payload of 30 kg and can clear obstacles 80 cm high; Dongtai Technology's robot finished the speed race in about 58 minutes with roughly 80% battery remaining.
AMI, the world model company founded by LeCun, together with New York University, INRIA Paris, and Brown University, released a paper on H-JEPA, proposing a hierarchical world model that stacks multiple JEPAs layer by layer for visual planning.
DeepBlue Embodied Intelligence examines the debate over embodied intelligence approaches along six main technical lines: modular planning, skill orchestration, imitation learning, reinforcement learning, VLA, and world models, drawing on 12 highly cited surveys from the past decade. The article notes that each approach answers the question of what robots should learn from, that the classic problems have not disappeared, and that what has changed is that the technical units for solving them are growing larger. It also mentions an industry estimate that general-purpose robots would need 100 million hours of data to reach a 70%–80% baseline success rate, and that more than 100 open-source embodied foundation models appeared worldwide in the past 18 months.
In Lecture 7 of the "Twenty-One Lectures" series, the Xbotics Embodied Intelligence Lab converts the target object pose obtained in Lecture 6 into gripper actions, linking the grasp-and-place loop with five poses—pre-grasp, grasp, lift, place, and retreat—and a state machine.
The BMW Group and Embotech say they have used Automated Driving In-Plant technology to move a cumulative 1 million vehicles at four production sites in the UK and Germany, with roughly 3,500 vehicle movements per day and availability above 99.5%.
Gu Yue Ju analyzes the PlaCo humanoid gait pipeline: a linear inverted pendulum trajectory optimization using jerk as the decision variable keeps the ZMP inside the support polygon, cubic splines connect the swing foot, and weighted QP inverse kinematics maps the center of mass and both foot targets into 26-dimensional joint velocities, completing continuous turning walking.
Gu Yue Ju analyzes the MuJoCo real-time predictive control framework, which uses a residual cost to unify task descriptions, with four planners—predictive sampling, gradient descent, iLQG, and hybrid ILQS—replanning at every step within the same loop. A Cartpole comparison experiment reports the convergence speed and per-step computational cost of the four.
The article explains Ruckig's jerk-limited online trajectory generation, covering the seven-segment profile of the triple-integrator-chain time-optimal problem, the selection of synchronization instants across multiple axes, and the closed-form solution for braking when limits are exceeded. It also presents measured tracking and target-jump replanning results for a two-joint arm in MuJoCo.