Designing Smarter Soft Robots with a Unified Approach
![A novel basis function design embeds material distribution via [latex]\arg\max[/latex] evaluation of a score field, enabling optimized swimmer trajectories-achieved through joint optimization-that outperform both sequential optimization and neural field encoding methods prone to lateral drift.](https://arxiv.org/html/2603.06497v1/x1.png)
Researchers have developed a new method for simultaneously optimizing a soft robot’s shape, material properties, and actuation, paving the way for more adaptable and efficient designs.
![A novel basis function design embeds material distribution via [latex]\arg\max[/latex] evaluation of a score field, enabling optimized swimmer trajectories-achieved through joint optimization-that outperform both sequential optimization and neural field encoding methods prone to lateral drift.](https://arxiv.org/html/2603.06497v1/x1.png)
Researchers have developed a new method for simultaneously optimizing a soft robot’s shape, material properties, and actuation, paving the way for more adaptable and efficient designs.
Artificial intelligence and self-driving laboratories are poised to dramatically speed up the design of catalysts and chemical reactions.

Researchers have created an embodied AI system capable of partnering with artists to co-create drawings, pushing the boundaries of human-robot creative collaboration.
![The molecule’s interconnectedness, as mapped in its connectivity matrix, reveals the fundamental architecture underlying MDMA’s properties - a network where each atom’s relationships define the substance’s behavior and potential interactions, expressed as [latex] \mathbf{A} [/latex].](https://arxiv.org/html/2603.05525v1/x1.png)
Turning chemical structures into data that artificial intelligence can understand is crucial for accelerating discovery in both chemistry and materials science.
Researchers have created a new multilingual corpus of both original and simplified texts to improve accessibility for individuals with varying literacy levels in civic participation.
New research shows that effective user training is crucial for successful adoption and performance gains when applying generative AI tools to complex legal analysis tasks.

New research demonstrates that explicitly understanding what other drivers intend to do, rather than simply predicting their movements, significantly improves the performance of autonomous parking systems.
Researchers have developed a standardized guideline for identifying and visualizing the core arguments within Chinese judicial rulings, paving the way for advanced legal analytics.

This paper details an efficient approach to creating Python interfaces for complex C++ robotics libraries, unlocking their power for a wider range of applications.
![The Keller-Segel model [latex] (2.33) [/latex] demonstrates diverse spatiotemporal patterns of aggregation depending on the final simulation time, highlighting the system’s sensitivity to temporal parameters.](https://arxiv.org/html/2603.04931v1/2603.04931v1/x12.png)
This review explores how multiple species interact and organize themselves using chemical signals, revealing the complex patterns that emerge from simple rules.