Tagged articles
multimodal perception
13 articles · Page 1 of 1
AntTechNov 9, 2026 · Artificial Intelligence
Ant Group open-sources LingBot-Touch, a tactile foundation model pre-trained on 5,000 hours of real data that unifies magnetic, visual, and resistive sensor signals into a shared representation, enabling cross-sensor, cross-hand, and cross-task reuse; integration with four action models across 26 real-robot tasks raises success rates by 14–26 percentage points.
LingBot-Touchcross-sensor generalizationdexterous manipulation
0 likes · 10 min read
Researchers from Renmin University and Beijing Academy of Artificial Intelligence introduce ROMA, a system that equips robots with multisensory active perception, enabling them to autonomously decide which object to interact with, how to interact, and which modalities to use, forming a reasoning-interaction-feedback loop that matches GPT-6 Astra performance on real-world tasks.
Qwen 2.5-OmniROMAROMA Bench
0 likes · 11 min read
Amap TechAug 20, 2026 · Artificial Intelligence
The article analyzes how Gaode Momentum’s TuTu robot dog overcomes high deployment costs by using map‑free spatial understanding, multimodal perception, and a unified embodied AI brain to enable reliable autonomous navigation and task execution across five diverse real‑world scenarios.
autonomous navigationembodied AImultimodal perception
0 likes · 11 min read
OpenAI’s July 2026 launch of ChatGPT Work, driven by GPT‑5.6, introduces a multi‑layer architecture that adds long‑context memory, native tool use and multimodal perception, enabling the model to operate real software, generate shareable sites, and compete with Anthropic and Google agents while exposing latency, security and cost challenges.
AI agentsChatGPT WorkGPT-5.6
0 likes · 11 min read
Amid a booming Chinese embodied‑intelligence market, RuoYu Technology’s explosion‑proof robot RuoYu LanYue 01, powered by the self‑developed RuoYu Jiutian brain, achieved the nation’s first explosion‑proof certification and the world’s first fueling‑brain solution, demonstrating end‑to‑end perception‑planning‑execution across fueling stations, oil‑gas fields, and ports.
H-GARembodied AIexplosion-proof robotics
0 likes · 16 min read
The TacForeSight study introduces a force‑conditioned tactile world model that predicts short‑term contact dynamics, integrates these predictions into a proactive policy, and demonstrates superior real‑time performance on five contact‑rich tasks compared with visual‑only and multimodal baselines.
contact‑rich tasksforce‑guided world modelmultimodal perception
0 likes · 9 min read
The article analyzes how the Dexterity‑BEV approach unifies heterogeneous robot sensor streams into a single bird's‑eye‑view coordinate system, aligning vision, state, action, and time to enable scalable, generalizable embodied AI, drawing parallels with the transformative impact of BEV in autonomous driving.
BEVDexterity-BEVGeneralization
0 likes · 11 min read
This survey systematically reviews Embodied AI security, proposing a five‑layer taxonomy (perception, cognition, planning, action & interaction, agentic system) that organizes over 400 papers on attacks, defenses, and open challenges, and highlights overlooked vulnerabilities such as multimodal perception fusion and planning instability under jailbreak attacks.
AI securityadversarial attacksembodied AI
0 likes · 26 min read
The 9th Tsinghua Big Data Intelligent Lecture gathered leading scholars and industry experts to showcase cutting‑edge research on multimodal perception, embodied intelligence, spatial AI, large‑model multimodal systems, and industrial time‑series databases, emphasizing their technical depth and real‑world impact.
GLM5V TurboSenseNovaartificial intelligence
0 likes · 8 min read
This article explains how to use NVIDIA Isaac Lab and the TiledCamera component to run large‑scale, multimodal reinforcement learning on GPU clusters, covering environment setup, noVNC visualization, command‑line execution, distributed training with torchrun, and performance analysis across multiple GPU configurations.
GPU scalingNVIDIA Isaac LabReinforcement Learning
0 likes · 12 min read
Amap TechFeb 13, 2026 · Artificial Intelligence
ABot‑M0 tackles the three long‑standing "Babel Tower" challenges of embodied AI—data fragmentation, inconsistent representations, and training mismatches—by releasing the massive UniACT dataset, introducing Action Manifold Learning for direct action prediction, and designing a plug‑and‑play dual‑path perception architecture that outperforms prior models on multiple robot benchmarks.
Datasetaction manifold learningembodied AI
0 likes · 14 min read
Researchers from Beihang University present a high‑low UAV collaborative navigation paradigm, introducing the HaL‑13k dataset and AeroDuo framework, detailing high‑altitude planning with Pilot‑LLM, low‑altitude three‑stage search, and demonstrating superior target finding in complex environments.
AeroDuoDatasetPilot-LLM
0 likes · 7 min read
In April 2018, Tsinghua University and Alibaba launched a joint Natural Interaction Experience Lab to explore next‑generation human‑machine interaction, aiming to give machines five senses and emotional understanding, and to apply this research across retail, smart homes, autonomous driving, and other emerging AI‑driven scenarios.
AIAlibabaHuman-Computer Interaction
0 likes · 8 min read
