Xiaoyu Han of University College London and Dongkun Han of the Chinese University of Hong Kong proposed SCET-CBF, a speed-calibrated soft guidance law for one-step dynamic navigation. It uses a short lateral escape maneuver to provide an allowable approach speed, and lets a quadratic program weigh the two effects of braking when choosing acceleration and steering.
The authors propose Neuromorphic Decision Dynamics (NDD), a decentralized, event-driven controller for safe navigation in congested environments, with guarantees on safety, liveness, robustness, and scalability. NDD requires no communication, preassigned priorities, or models of neighbors' objectives; by coupling internal decision and attention states to physical states and the relative motion observed locally, it enables agents to self-organize into local conflict groups and form a passage order.
The study proposes a modular perception-prediction-planning pipeline that propagates uncertainty as structured, interpretable quantities across modules and guarantees a feasible solution in every cycle within convex safe sets. In Monte Carlo trials at a four-way unsignalized intersection, the pipeline achieved 0% collisions and 0% solver infeasibility, with 12.7 ms per cycle; the deterministic planner and chance-constrained baseline had collision rates of 36% and 10%, respectively. Ablation experiments confirmed the necessity of each uncertainty source, and a hardware deployment on a Clearpath Jackal UGV verified real-time feasibility.
LANav targets the open-vocabulary object goal navigation (OVON) task, in which a robot must find a target in an unfamiliar indoor environment using only its current first-person image. Its approach is to have the robot stop repeatedly reviewing past frames and instead organize its memory to support navigation decisions.
Cortical Labs' biological computer CL1, built from living cells, was trained in a simulated 2D environment and then used to control the movement of a real robot dog. A paper from the company that has not yet been peer-reviewed shows that the neural network improved over time when continuously fed the same data, and Ferrante Neri of the Education University of Hong Kong considers this preliminary evidence of learning from limited experience. Cortical Labs says the biological computer may consume less energy than digital approaches, and its cells come from blood stem cells donated with donor consent.
Researchers developed a single control policy that lets Unitree's G1 complete ladder climbing, crawling, obstacle traversal, stepping stones, and recovery after falls by deciding the placement of nine different body parts. The robot can use its hands, elbows, knees, feet, and even pelvis for support rather than relying only on walking, achieving a 92.5% success rate on a simulated obstacle course, but how this flexibility performs in unpredictable real-world environments remains a bigger test.
Researchers from Tsinghua University and the National University of Singapore propose ParallelWorld, which adds multi-step candidate future rehearsal to high-level planning for embodied agents, raising task success rate from 56% to 83%. The method generates and verifies multiple candidate action branches in a rehearsal loop; during execution it takes only the first action of the selected trajectory, then replans based on new observations. Success rates were higher than the direct baseline across eight LIBERO-Pro settings, but adaptive search took on average about 5.8 times as long as direct execution.
DeepMirror released a full-stack physical AI solution for the steel industry at the 2026 Unitree Technology Partner Ecosystem Conference held in Hangzhou on October 22. Using Unitree quadruped robot dogs as the carrier and paired with its self-developed Insight series spatial intelligence cameras, the Navcore spatial intelligence brain, and a task management platform, the solution enables a complete inspection chain covering pure vision positioning, autonomous navigation, dynamic obstacle avoidance, equipment detection, and data archiving. The solution has been deployed at multiple steel enterprises including Xiangtan Iron and Steel and Jinnan Iron and Steel, has entered a phase of regular on-site operation, and is planned for reuse in scenarios such as power cable tunnels and chemical industrial parks.
The study proposes Embodied Agent Arena, evaluating ten VLM agents across five dimensions—geometry, spatial reasoning, affordance, task planning, and manipulation—with 1,000 cases, including the 168-case GeoProbe benchmark for camera, motion, depth, and scale estimation.
The paper proposes Environmental Constraint Exploitation (ECE), a method that deliberately makes contact with the environment to reduce the dimensionality and computational complexity of motion planning. The authors integrate ECE into an RRT-based planner, biasing exploration toward task-relevant regions and using contact to reduce uncertainty and improve execution robustness, and demonstrate practical results in real-world scenarios. The work consolidates and extends prior research, showing that ECE can simplify motion planning and enhance adaptability in complex environments.
The authors propose VORL-EXPLORE, a hybrid learning and planning framework that uses execution fidelity to estimate local navigability and execution reliability, coupling it into a Voronoi allocation objective with inter-robot repulsion and arbitrating during navigation between global A* guidance and a reactive reinforcement learning policy. The fidelity model is recalibrated using self-supervised pseudo-labels generated from recent progress and safety outcomes. Experiments on randomized dynamic grids and an ablation under severe congestion show higher success rates, shorter exploration paths, and lower inter-robot coverage overlap, along with a deployment example in a Gazebo factory scenario; the code is open-sourced.
The authors propose Consistent Action-Response Execution (CARE), which grounds local control in executable-action-indexed joint human-robot transitions, so that the same executable action simultaneously determines operator response prediction, joint human-robot rollout, and candidate selection. On training and held-out maps, CARE maintains near-saturated performance when the indicated route remains locally passable, and achieves the highest success rate and service availability when the operator can continue but the robot must detour.
A research team completed an on-orbit demonstration on the International Space Station's Astrobee free-flying robot of machine learning-based warm starts to accelerate trajectory optimization, using a neural network to predict initial values for a sequential convex programming (SCP) solver, which then enforces safety constraints. In scenarios including rotational dynamics, the trained network reduced the number of solver iterations required for convergence by 60%, and by 50% in obstacle scenarios drawn from the training distribution. The work was published at iSpaRo 2025.
The authors propose the SAGE (Semantic-to-Action Grounded Execution) framework, which uses trajectories output by a vision-language model (VLM) as preferences over complete geometric candidate paths, and combines each candidate's geometric score with its agreement with the VLM trajectory through rank fusion.
The paper proposes a natural-language policy interface that connects operator instructions to ROS 2 Nav2: a local large language model converts instructions into JSON policies specifying destinations, spatial constraints, and temporal or event conditions; deterministic checks then decide whether to accept them, and three costmap adapters inject them into the existing navigation stack without changing the planner or controller.
The authors propose OWLS (Open-world Language-conditioned Speed Fields), which plans directly over the dense feature maps of a vision-language model (VLM): given a description of traversable terrain, the VLM scores every pixel of a single camera image, and OWLS projects these scores onto the ground, adapts them to the platform with two morphological operations, and uses them as the speed field of a minimum-time planner, so that terrain appearance and obstacle spacing jointly shape a single trajectory.
UAV-SwarmAgent is a hierarchical multi-agent system in which an operator issues a mission in one natural-language sentence, and a ground-station agent generates and executes code that turns it into routes for each UAV. The system uses a vision-language model to locate inspection targets on an aerial map, balances them among N UAVs by route length, and then worker agents equipped with lightweight decision models verify incidents.
The authors propose HGWM, which combines an LLM-generated room-anchor prior with persistent spatial-semantic memory to select search directions in zero-shot object navigation. On HM3D v0.1, it reports 62.6% success rate and 31.5% SPL, versus 58.1% and 31.2% for WMNav; on MP3D, 46.8% and 17.9%, versus 45.4% and 17.2%.
The v1 lecture notes "Optimization, Optimal Control, and Reinforcement Learning for Robotics," compiled and edited by Yonghyeon Lee, have been released on arXiv, emphasizing the mathematical connections and practical applications among the three. The notes were written through human-AI collaboration and are a compilation of existing material rather than new research results; they are currently a preliminary version with no figures or graphs, and revisions and expansion are planned.
This research proposes a unified control framework that shifts multi-robot systems from "obligate swarms" constrained to pure self-organization toward "facultative swarms"—hybrid architectures that operate with centralized planning when conditions are permissive and degrade smoothly into decentralized swarming under environmental stress. The authors argue for redefining swarming behavior as a dynamic capability rather than a fixed system category, thereby exploiting centralized optimality when conditions allow and the flexibility of self-organization when they do not.
The authors propose the Graphs of Trajectory Bundles (GTB) method, which combines sampling-based motion planning, trajectory optimization, and graph search for motion planning of systems with nonlinear and even black-box dynamics. Based on a graph-of-convex-sets decomposition of the workspace, the method iteratively constructs a graph of trajectory bundles that captures the local dynamics at each vertex, then solves a shortest-path problem on the graph to obtain trajectories that satisfy the system dynamics and constraints such as collision avoidance and safety in the limit. The authors claim it can handle highly nonlinear, unstable, and even black-box dynamics with complex constraints.
TravSUITE is a traversability system for high-speed off-road navigation, consisting of a voxel mapper that uses visual foundation models to build a geometric-semantic local map and a unified neural network that jointly predicts geometry, semantics, speed, and cost in bird's-eye view (BEV).
The study proposes a modular framework that combines neural cellular automata (NCA) with existing site selection and collision-aware control for swarm robot morphogenesis. The framework introduces a decentralized attachment-site discovery mechanism in which robots already in place identify new attachment sites by updating and sharing local NCA states, eliminating the need for a predefined site list during deployment. The authors also propose offline sparse-retention fine-tuning and a false-positive loss to bridge NCA growth and gradual physical assembly. Simulations scale to several hundred robots and improve morphology accuracy, and experiments with Crazyflie quadrotors validate the integrated execution pipeline.
The authors propose RepresentNav, a navigation foundation model that uses Representation Residuals, a three-layer transformer, to aggregate full-depth features from multiple vision foundation models and construct a representation space driven by the policy's own objectives.
Why it matters: The paper proposes constructing a visual representation space using the policy's own objectives and predicting future scene representations within it, offering transferable ideas for the representation design of navigation policies.
Without modifying the AGV PLC program, the Kollmorgen NDC scheduling system uses configurations such as TS, Cluster, Blocking, Weight, and SSIO in System manager/System manager NG to implement three traffic management solutions for oncoming traffic on narrow paths.
At the 26th China International Industry Fair, CAS Fifth Century used three Jiling-L1 wheeled dual-arm robots to relay a continuous material flow of depalletizing, pouring, receiving, and palletizing, with no manual intervention throughout. At the same event, it launched the column-type embodied intelligent robot Jiling-S1, featuring 19 degrees of freedom and 360° waist rotation, and introduced its next-generation embodied brain Jiyuan Lingnao, which relies on its self-developed FAM series embodied large models and motion optical flow technology to explore cross-embodiment transfer and few-shot learning.
At Nvidia GTC Berlin 2026, Kion jointly showcased warehouse physical AI applications with Nvidia and Accenture; an autonomous vehicle fleet is already working alongside employees and manually driven vehicles at GXO's warehouse in Épinoy, France.
The study proposes OSMA-Bench, an obstacle-conditioned safe motion adaptation benchmark built on spatially matched scenario sets that differ only in obstacle type, and introduces the Semantic Sensitivity Index (SSI) to measure whether a robot's clearance and its distance-dependent speed and smoothness follow the caution ordering of obstacles.
Deep Blue AI published an article outlining the division of labor among VLA, WAM, and Harness in embodied systems: VLA turns observations and goals into actions, WAM uses future-state prediction to aid action learning, and Harness organizes subtasks, capability invocation, and execution feedback.
At the 140th Canton Fair, AgiBot Elf G2, Zhidong Future's "Xiaozhi," and Dongyi Technology's PHYBOT C-series bipedal humanoid robots moved from exhibition booths to actual roles, taking on tasks such as subway guidance, showroom presentations, and autonomous badminton and table tennis rallies, with service continuing until November 4. Dongyi Technology supports cross-scenario capability transfer with the PhyAgents decision-making agent in its Embodied PhyStack architecture and has launched a modular deployment kit, PhyAgents Hub. The industry is also exploring two commercialization paths: systematic foundations and positioning in vertical scenarios such as those of CloudMinds.
DEEP Robotics has released five research results built around its self-developed embodied brain, DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark.
During the 2026 QinCheng Conference, the Amap Momentum robot dog Tutu took part in guided explanations and tours, and together with Alibaba Group General Affairs and QinCheng Smart, released a smart campus case study and joint solution, bringing Tutu's inspection work at the Hangzhou Xixi Campus into the spotlight. Amap divides the ABot system into three layers—DATA, MODEL, and AGENT—supported by the ABot-N1 navigation base and the ABot-M0.5 manipulation base, and adopts a dual-speed architecture of cloud-based macro planning plus on-device embodied execution.
DEEP Robotics has released five research results built around its self-developed embodied brain DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark. Partners include seven universities, among them MIT, Tsinghua University, and Zhejiang University.
A research team from Harvard, NVIDIA, Berkeley, MIT and Stanford proposes RAX (Robot Agent eXploration), which connects a general coding agent to robot perception and control interfaces, uses online exploration to write successful decisions into executable programs and accumulate them as reusable skills, while keeping model parameters frozen.
Why it matters: RAX uses a frozen model plus online exploration to generate reusable programs, leading by an average of 37.4 percentage points on five simulation benchmarks with zero action demonstrations, offering a path for robot learning different from scaling data and models.
Registration is open for the RoboWorld Challenge 2026, which features three tracks: WorldNav, HA-VLN 2.0, and SafeDrive-VLA. They respectively test language-guided open-loop route planning, social navigation in dynamic crowds, and safe driving under conflicting instructions. The final submission deadline is November 30, 2026.
DEEP Robotics has released five research results built around its self-developed embodied brain DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark. The company says the work was carried out jointly with seven universities, including MIT, Tsinghua University, and Zhejiang University.
AgiBot organized 110 Expedition A3 humanoid robots to complete a group dance challenge at the Jinan Yellow River International Convention and Exhibition Center, with a Guinness World Records adjudicator presenting the certification on site. The challenge relied on the self-developed LinkBots group control and scheduling system to uniformly manage motion trajectories, action timing, and formation changes, combined with UWB centimeter-level fusion positioning and 5G/WiFi dual-mode communication to achieve millisecond-level synchronization, and supports fault isolation and empty-slot avoidance. These robots will subsequently enter subway stations, scenic areas, and other settings to take part in information guidance, patrol assistance, and cultural tourism performances.
The University of Hong Kong and Tsinghua University propose VAST (Horizon Adaptive Offline Policy Learning via Value Stitching), an offline value learning framework that adaptively selects update horizons by jointly choosing future subgoals and time spans to stitch local returns with subsequent values.
In Jinan, Shandong, AgiBot had 110 Expedition A3 full-size humanoid robots dance simultaneously, setting a Guinness World Record for "most humanoid robots dancing simultaneously." The attempt relied on AgiBot's Lingdong LinkBots swarm control platform and UWB centimeter-level positioning technology to achieve synchronized multi-robot movements and formation changes. These robots will later be deployed in cultural tourism performances, public services, scientific research and education, and other scenarios.
Limpid Intelligence founder Li Yiming's team at Tsinghua University released the world action model PrismWAM and the execution diagnosis framework RoboDoctor. PrismWAM decouples semantic context from physical state and, without additional action-data pretraining, achieved an average success rate of 83.67% on RoboTwin 2.0 and 75.5% in the Clean-to-Random setting, ranking first on the official leaderboard.