MAROKO133 Breaking ai: Parking woes gone? Robotic systems manage tight spaces in garages w

📌 MAROKO133 Update ai: Parking woes gone? Robotic systems manage tight spaces in g

Automated parking robots are moving from novelty to real-world deployment, and a system rolling out in South Korea shows how much reliable connectivity matters to making that shift work at scale.

HL Robotics has developed an automated parking solution called Parkie, designed to remove the stress from parking in tight, crowded lots.

Instead of drivers hunting for space, robots take control of the vehicle and move it into position autonomously.

The system is already operating in real parking facilities, where multiple robots move vehicles at the same time. The key challenge is not the mechanics alone, but keeping every robot connected at all times inside concrete-heavy, multi-level garages.

For this kind of setup, even brief communication loss can stop operations or create safety risks. That is where industrial-grade wireless networking becomes central to the system’s design.

At the core of Parkie’s operation is a wireless backbone that allows robots to coordinate movements, receive commands, and relay status data in real time while constantly on the move.

Connectivity makes automation possible

Each parking robot depends on continuous, low-latency communication to function safely. Robots must know their exact position, coordinate with other units, and adjust movement instantly.

Parking garages are difficult wireless environments. Thick concrete walls, metal structures, moving vehicles, and changing layouts can disrupt standard Wi-Fi connections.

HL Robotics uses Cisco’s Ultra-Reliable Wireless Backhaul (URWB) to maintain uninterrupted communication. The technology is designed for industrial environments where dropped signals or latency spikes are unacceptable.

URWB supports near-zero latency and lossless communication, allowing robots to move while staying connected. It enables seamless handoffs between access points using a make-before-break approach, ensuring the connection remains active even as robots roam across coverage zones.

Another feature, multipath operations, sends high-priority traffic across multiple paths and frequencies simultaneously. This helps prevent packet loss when several robots move at once or when radio conditions change.

Cisco’s system also includes built-in monitoring tools that log network status in real time. If a disruption occurs, operators can quickly identify where and when it happened and respond without shutting down the system.

Robots built for real lots

Parkie is designed to work in a wide range of parking facilities, from small garages to large commercial structures. Fleets can scale from a few robots to more than ten operating simultaneously.

The robots handle precise positioning, reduce the risk of door damage, and allow vehicles to be parked closer together. This can increase parking capacity without expanding physical space.

Beyond parking, the system reflects a broader trend in robotics. As robots move into public infrastructure, wireless reliability becomes just as important as mechanical design.

Cisco positions the same rugged networking technology used in Parkie for other harsh environments, including factories, logistics hubs, and outdoor industrial sites. These networks are built to withstand temperature swings, moisture, vibration, and physical obstructions.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Breaking ai: Adobe Research Unlocking Long-Term Memory in Video World

Video world models, which predict future frames conditioned on actions, hold immense promise for artificial intelligence, enabling agents to plan and reason in dynamic environments. Recent advancements, particularly with video diffusion models, have shown impressive capabilities in generating realistic future sequences. However, a significant bottleneck remains: maintaining long-term memory. Current models struggle to remember events and states from far in the past due to the high computational cost associated with processing extended sequences using traditional attention layers. This limits their ability to perform complex tasks requiring sustained understanding of a scene.

A new paper, “Long-Context State-Space Video World Models” by researchers from Stanford University, Princeton University, and Adobe Research, proposes an innovative solution to this challenge. They introduce a novel architecture that leverages State-Space Models (SSMs) to extend temporal memory without sacrificing computational efficiency.

The core problem lies in the quadratic computational complexity of attention mechanisms with respect to sequence length. As the video context grows, the resources required for attention layers explode, making long-term memory impractical for real-world applications. This means that after a certain number of frames, the model effectively “forgets” earlier events, hindering its performance on tasks that demand long-range coherence or reasoning over extended periods.

The authors’ key insight is to leverage the inherent strengths of State-Space Models (SSMs) for causal sequence modeling. Unlike previous attempts that retrofitted SSMs for non-causal vision tasks, this work fully exploits their advantages in processing sequences efficiently.

The proposed Long-Context State-Space Video World Model (LSSVWM) incorporates several crucial design choices:

1. Block-wise SSM Scanning Scheme: This is central to their design. Instead of processing the entire video sequence with a single SSM scan, they employ a block-wise scheme. This strategically trades off some spatial consistency (within a block) for significantly extended temporal memory. By breaking down the long sequence into manageable blocks, they can maintain a compressed “state” that carries information across blocks, effectively extending the model’s memory horizon.
2. Dense Local Attention: To compensate for the potential loss of spatial coherence introduced by the block-wise SSM scanning, the model incorporates dense local attention. This ensures that consecutive frames within and across blocks maintain strong relationships, preserving the fine-grained details and consistency necessary for realistic video generation. This dual approach of global (SSM) and local (attention) processing allows them to achieve both long-term memory and local fidelity.

The paper also introduces two key training strategies to further improve long-context performance:

• Diffusion Forcing: This technique encourages the model to generate frames conditioned on a prefix of the input, effectively forcing it to learn to maintain consistency over longer durations. By sometimes not sampling a prefix and keeping all tokens noised, the training becomes equivalent to diffusion forcing, which is highlighted as a special case of long-context training where the prefix length is zero. This pushes the model to generate coherent sequences even from minimal initial context.
• Frame Local Attention: For faster training and sampling, the authors implemented a “frame local attention” mechanism. This utilizes FlexAttention to achieve significant speedups compared to a fully causal mask. By grouping frames into chunks (e.g., chunks of 5 with a frame window size of 10), frames within a chunk maintain bidirectionality while also attending to frames in the previous chunk. This allows for an effective receptive field while optimizing computational load.

The researchers evaluated their LSSVWM on challenging datasets, including Memory Maze and Minecraft, which are specifically designed to test long-term memory capabilities through spatial retrieval and reasoning tasks.

The experiments demonstrate that their approach substantially surpasses baselines in preserving long-range memory. Qualitative results, as shown in supplementary figures (e.g., S1, S2, S3), illustrate that LSSVWM can generate more coherent and accurate sequences over extended periods compared to models relying solely on causal attention or even Mamba2 without frame local attention. For instance, on reasoning tasks for the maze dataset, their model maintains better consistency and accuracy over long horizons. Similarly, for retrieval tasks, LSSVWM shows improved ability to recall and utilize information from distant past frames. Crucially, these improvements are achieved while maintaining practical inference speeds, making the models suitable for interactive applications.

The Paper Long-Context State-Space Video World Models is on arXiv

The post Adobe Research Unlocking Long-Term Memory in Video World Models with State-Space Models first appeared on Synced.

🔗 Sumber: syncedreview.com