{"id":385,"date":"2025-01-12T21:38:11","date_gmt":"2025-01-12T21:38:11","guid":{"rendered":"https:\/\/yingkeli.me\/?page_id=385"},"modified":"2025-08-24T22:27:27","modified_gmt":"2025-08-24T22:27:27","slug":"acc-2025-workshop-for-optimizing-across-scales","status":"publish","type":"page","link":"http:\/\/yingkeli.me\/index.php\/acc-2025-workshop-for-optimizing-across-scales\/","title":{"rendered":"ACC 2025 Workshop"},"content":{"rendered":"\n
<\/span>\"\"
\n

Optimizing Across Scales:<\/strong>
Multi-Fidelity, Multi-Modality, and Multi-Objective Approaches for Complex Systems<\/strong><\/p>\n\n\n\n

Date: July 7th, Monday, 2025<\/h3>\n\n\n\n

Time: 8:30 – 17:00, Mountain Standard Time<\/h3>\n\n\n\n

Location: Denver, Colorado, USA<\/h3>\n<\/div><\/div>\n\n\n\n

Remote participation available!<\/h4>
Register to receive Zoom link and materials.<\/div><\/div>
\n
Register Here<\/span><\/a><\/div>\n<\/div><\/div><\/div><\/div>\n\n\n\n
\n\n\n\n

Abstract<\/strong><\/h2>\n\n\n\n

As robotics systems scale in complexity\u2014from single agents to large autonomous fleets\u2014they must navigate an intricate landscape of trade-offs across multiple dimensions<\/strong>, balancing accuracy and efficiency, adaptability and robustness, and competing objectives in real-time decision-making. This workshop explores how multi-scale optimization strategies<\/strong> can address these challenges and achieve a \u201csweet spot<\/strong>\u201d of those trade-offs, enabling robotics and intelligent systems to operate seamlessly across scales. Through cross-disciplinary perspectives spanning control, robotics, and bio-inspired engineering<\/strong>, attendees will gain insights into how to navigate real-world trade-offs<\/strong>, bridging theoretical advancements with practical deployment in<\/strong> robotics and beyond.<\/p>\n\n\n\n

Optimization across scales is a fundamental aspect of intelligence, balancing trade-offs across various dimensions\u2014from learning<\/strong> to synthesis<\/strong> to decision-making<\/strong>. For learning<\/strong>, the trade-off between accuracy and efficiency<\/strong> can be managed by leveraging models with multiple fidelity levels<\/strong>, ensuring effective usage of computational resources. In synthesis<\/strong>, achieving a balance between consistency and variability<\/strong> is critical when extracting and integrating information from multiple modalities<\/strong>. For decision-making<\/strong>, compromises among multiple objectives<\/strong> are often unavoidable due to conflicting goals, demanding ethical<\/strong> considerations. These multi-scale optimization strategies are prerequisites to unlocking the full potential of intelligent systems, enabling them to generate emergent forms of intelligence at higher, more complex levels.<\/p>\n\n\n\n

Therefore, this workshop aims to explore multi-fidelity, multi-modality, and multi-objective optimization approaches<\/strong>, with a focus on how these methods can enhance efficiency, accuracy, consistency, variability, and ethicality. More specifically, tracking complex problems that involve:<\/p>\n\n\n\n