Agenda

Across healthcare, logistics, manufacturing, and public spaces, robots are increasingly operating alongside people. This marks the era of Physical AI, where perception, autonomy, and software-defined intelligence intersect with the real world. When humans and robots share space, there are no second chances.

This session will explore the foundational software and critical building blocks that enable safe autonomy at scale. As robotics transitions from contained automation to open deployment, safety must move beyond being an afterthought or a compliance checkbox—it needs to be integrated into the heart of every system and continuously enforced as environments and software evolve.

Together with executives from QNX, Amazon Robotics, Locus Robotics, and Universal Robots, we’ll discuss how leading organizations are tackling autonomy at scale, balancing innovation with predictability, and weaving safety, security, and real-time performance into their solutions. Drawing from real-world deployments, the panel will examine what it takes to build robotics systems that people can confidently trust to operate around them every day, as intelligence takes its place in the physical world.

While substantial progress has been made in the functional safety of modern robotics, the integrity of the software build process remains largely unaddressed. This talk exposes the silent risk of toolchains: the reality that latent compiler or library defects can systematically corrupt the core THINK and ACT loops of a robotic system. When the translation from high-level safety logic to machine code is flawed, even a perfectly designed perception-action cycle can fail, leading to catastrophic physical outcomes.

This risk is further amplified by the increasing need for frequent software updates, driven by cybersecurity requirements and continuous product improvement. These updates can invalidate previously trusted toolchain baselines, creating an ‘update paradox’ that slows both deployment and innovation. At the same time, the introduction of the EU Machinery Regulation makes this issue unavoidable. If a robot uses AI or machine learning in its safety functions—such as an AI vision system governing the THINK phase of collision avoidance—it is classified as high-risk machinery. Under this new regime, toolchain trust must be explicitly demonstrated. The regulation recognizes that the tools used to build software are as vital as the code itself; therefore, toolchain qualification is no longer an optional checkbox, but a prerequisite for market access.

Taken together, this regulatory shift and the update paradox fundamentally redefine the build process. Qualification can no longer be a one-off certification step; it must evolve into a continuous process that maintains trust across updates, toolchain changes, and evolving system requirements. By reframing compilers and libraries as active components of the functional safety chain, this talk provides a roadmap for closing the trust gap—enabling safer robots and sustained compliance in the age of physical AI.

You have invested in connecting CAD to your other workflow systems in hopes of creating a continuous flow of mission-critical data. But somewhere in a shared drive, a locally saved PDF, or an engineer's inbox, there's a parallel universe of untapped data — work instructions, PRDs, maintenance manuals, install guides — that your systems can't read, your LLMs can't parse, and your workflows can't touch. It's the largest untapped data source in hardware, and most teams don't even know they're sitting on it. This presentation examines how documentation has become the largest untapped data source in hardware and manufacturing, and what it takes to change that. Whether you're trying to feed better context into AI workflows, reduce tribal knowledge loss, or close the gap between engineering intent and production reality, the answer is probably already written down somewhere. This talk will show you how to find it.

As robots move into more dynamic, unstructured environments, joint design has become one of the most critical, and often most complex elements of robotic system performance. From payload capacity and precision to energy efficiency and maintainability, the way joints are engineered can significantly impact a robot’s overall capabilities and lifecycle cost. Yet many teams continue to build highly customized joint architectures that add unnecessary complexity, increase development time, and limit scalability.

This session explores how roboticists and design engineers can rethink joint design by more effectively leveraging modern servo actuators. Rather than treating actuators as off-the-shelf components to be retrofitted into bespoke designs, this talk will highlight the value of early, collaborative engagement with actuator manufacturers to co-develop solutions tailored to specific application requirements.

The robotics industry is entering a new era where success depends not just on innovation but on the ability to scale and deploy systems in real-world environments. While the breakthrough happens in the lab, the business happens post-design across an increasingly unpredictable public infrastructure. This panel assembles robotics industry leaders to bridge the gap between cutting-edge innovation and commercial viability, discussing challenges and opportunities.

Attendees can expect a deep dive into the operational "valley of death" and the strategies used to cross it. Key insights include:

• The Physical AI Frontier: How the convergence of generative models and robotics is shortening development cycles—and where it still hits a wall
• The Scaling Playbook: Hard-won lessons on transitioning from custom-built prototypes to high-volume manufacturing without sacrificing reliability
• Infrastructure & Supply Chain Readiness: Navigating the global hardware squeeze and ensuring your tech stack is compatible with legacy systems
• Winning the Trust of the End-User: Strategies for overcoming automation anxiety and demonstrating clear ROI to skeptical customers
• The Regulatory Landscape: Preparing for the shifting safety standards and compliance requirements that come with large-scale deployment

As robotics shifts from task automation to intelligent autonomy, the real challenge isn’t just building robots that move, it’s designing systems that learn, adapt, and earn trust at scale. John Black, CTO at Brain Corp, will unpack what it takes to build and deploy robot fleets that combine reliability with intelligence.

Drawing from Brain Corp’s experience powering over 40,000 robots worldwide, Black will explore how new approaches in perception, data integration, and continuous learning are redefining autonomy in real-world environments like retail, logistics, and public spaces. He’ll share how teams can bridge the gap between simulation and deployment, optimize for safety and privacy by design, and architect systems that evolve responsibly over time.

Attendees will gain a behind-the-scenes view of how to turn complex, dynamic environments into structured intelligence, and practical lessons on scaling robot software, managing edge-to-cloud data flows, and maintaining trust with users and regulators alike.

Soft wearable robots are transforming how people move, work, and recover. This talk will explore the engineering innovations behind next-generation soft robots—from new functional apparel innovations and actuation strategies to intelligent control and human–machine co-adaptation—and how these advances have translated into real-world impact.

Drawing on examples such as Verve Motion’s exosuits for industrial injury prevention, ReWalk’s ReStore for stroke rehabilitation, and Imago Rehab’s digital therapy platform, the talk will cover how academic research can move rapidly toward commercialization through user-centered design, clinical validation, and strategic partnerships. The talk will highlight both the engineering breakthroughs that enable these systems and their use cases spanning the factory floor, the clinic, and the home.

How do you transition from a successful prototype to a deployed fleet executing billions of autonomous trips in the real world? In this session, Teddy Ort, Senior Vice President of Robotics Software & AI at Symbotic, will offer a look under the hood at the engineering playbook required to seamlessly scale tens of thousands of robots.

While getting a single robot to work is an achievement, the true challenge of massive scale lies in taming the long tail of unpredictable edge cases. By embracing a cross-functional systems mindset and leveraging sophisticated perception and AI, robots can be empowered to dynamically adapt to changing physical environments. This talk will explore the practical realities of combining AI-driven optimization, large-scale simulation, advanced telemetry, and over-the-air updates to build resilient, world-class robotic solutions – and look at key developments we can expect in the years ahead.

Industrial worksites have long been among the most lucrative environments for robotics to deliver value in automation. This session will discuss the road to deploying modern AI-driven robotics and the opportunities and challenges along the way.

Generative AI is accelerating the automation of complex digital tasks, and now we are at an inflection point where multimodal perception and sensor understanding make physical AI the next frontier. This shift brings adaptive reasoning into the physical realm enabling natural interaction between humans and intelligent machines, from autonomous vehicles to humanoid robots.

While advanced self-driving systems helped pave this path, humanoids introduce a different set of constraints: long-horizon reasoning plus dexterous manipulation must run within a tight power and thermal envelope shared across compute, memory, and storage.

This presentation examines how memory and storage solutions must evolve to meet the application-specific requirements of humanoid robotics as it diverges from even the most advanced autonomous vehicles.

The robotics world is obsessed with foundation models and large behavior models (LBMs), but deployment is where that optimism meets reality. When AI hits a real-time embedded system on a NASA rover or an iRobot platform, the integration gap between cutting-edge models and deterministic, safety-critical software becomes the actual engineering problem.

This talk addresses that gap: what it takes to make LBMs deployable, why so many teams underestimate it, and where deterministic systems are simply the better engineering choice. It’s a practitioner’s view on the tension between LBM capability and production reality, from an engineering firm that has shipped on both.

AI‑ and RL‑driven control has enabled increasingly capable autonomous robots, yet real‑world deployment remains limited by the persistent sim‑to‑real gap. While most mitigation efforts focus on improving simulation or high-level control, this talk presents maxon’s complementary hardware‑first strategy. By integrating specialized firmware features and applying maxon’s deep understanding of drive‑system dynamics, key actuation and sensing nonlinearities are removed at their source. This approach delivers more predictable, simulation‑aligned behavior. Case studies from robotics partners illustrate how this approach boosts robustness, accelerates deployment, and enhances performance in real‑world autonomous systems.

Most conversations about warehouse automation focus on the technology, but not enough attention is paid to what it takes to make automation actually work in real-world environments. That means dealing with unpredictable environments, legacy systems, and shifting human workflows.

In this session, Anthony Jules, CEO of Robust.AI, draws on decades of experience in robotics to explore what it really takes to bring automation into complex warehouse environments. He’ll share practical insights from the field on what makes or breaks successful implementations, ranging from design decisions that support collaborative robots to the organizational changes required for adoption. Additionally, Anthony will discuss the real barriers to automation, the importance of making systems intuitive, and how to think about automation not as a replacement, but as a partner for human workers.

Model Context Protocol (MCP) has emerged as a standard for connecting AI systems with external tools, opening new pathways for collaboration between reasoning models and the physical world. The open-source Robot MCP project extends this standard to robotics—enabling AI models such as Claude, ChatGPT, and Gemini to perceive, plan, and act through existing robot ecosystems built on platforms like ROS.

This talk explores how the Robot MCP ecosystem is expanding through academic and industry partnerships to define open best practices, safety frameworks, and shared tool libraries. We’ll showcase how multi-agent orchestration—where perception, reasoning, and control agents coordinate through MCP—unlocks new forms of robotic autonomy and problem-solving.

By connecting the broader AI and robotics communities through a unified protocol, Robot MCP is shaping a future where intelligent agents and physical systems collaborate seamlessly, safely, and openly.

Robots don’t get smarter by accident; they improve through a deliberate data flywheel. This panel explores how real-world robot data is captured, curated, and fed back into perception, autonomy, and system performance. Drawing on lessons from field-deployed robots, we’ll explore how to design the data flywheel from day one, turning pilots into scalable, field-ready platforms that continuously learn and improve in production.

Touch is a key enabling modality in many surgical procedures. Recreating and augmenting the surgeon’s sense of touch in surgical robotics relies on innovations in compact, high reliability, scalable force-torque sensing technologies.

This session will give an overview of the roles of force and torque sensing in surgical robotics; including tip of instrument sensing, trocar remote center of motion/tissue contact, surgeon collaboration/leading/tool insertion, and surgeon-consol interfaces.

We’ll dive in core specifications and the state-of-the-art of what’s possible with force-torque sensing technologies, along with best practices for implementing the force-torque modality into surgical robots.

Designing robots for outdoor and extreme environments demands design considerations that can withstand the elements while delivering precise, consistent performance. This session explores how electric linear actuators and servo systems have evolved to meet the rigorous demands of field robotics—offering a robust alternative to traditional motion technologies in harsh conditions.

This session will help robotics engineers:

• Design motion systems that maintain performance and safety in the most challenging environments
• Select and validate components for reliability in field robotics, agriculture, defense, and energy sectors
• Apply best practices for cleanability, corrosion resistance, and mechanical resilience in outdoor robotic platforms

In a world where software dominates the headlines, robotics remains one of the few industries where hardware still truly matters. Drawing on over two decades of experience helping companies from startups to Fortune 500s bring their ideas to life, Ted will share what makes a great robotics company and what separates successful robots from those that never make it past the prototype stage. This session explores how the best robotics companies think about design, collaboration, and manufacturability from day one. Attendees will learn why hardware and software must evolve together, how to avoid common design mistakes that can derail even the most promising projects, and what qualities to look for in a reliable robotics development partner. Packed with real-world examples and practical lessons, this talk offers a clear roadmap for building robots that don’t just work in the lab, but thrive in the real world.

As robotics technologies advance, securing intellectual property is more critical—and more complex—than ever. This panel will explore practical IP strategies that robotics innovators can use to safeguard their inventions, navigate global patent landscapes, and maintain competitive advantage in a fast-evolving field. Speakers will address the following key points:

Implementing processes to identify and protect novel technologies

Ensuring strong protection for AI innovations, including balancing patent and trade secret options

Developing a strategic patent portfolio—using both offensive and defensive strategies—to secure a competitive edge in the robotics market

Understanding the robotics patent landscape to guide product development, avoid infringement risks, and align IP strategy with technological roadmaps

Attracting investment and strengthening collaboration and licensing opportunities

Preparing for IP due diligence from both the investor/acquirer and target perspectives, with an emphasis on the unique considerations in the robotics sector.

Robots are evolving from programmed ROS applications to embodied AI (LLMs running on physical robotics hardware) solving missions. New robotics AI tools are evolving such as VLMs (Vision Language Models also called multimodal LLMs), VLAs (Vision Language Action models), and MCP (Model Context Protocol) servers. Robots now stream sensors like RealSense depth cameras into these AI tools allowing the AI to figure out on its own how to move its wheels or legs to achieve a goal such as following a person. During this session, we will build an embodied AI experience together live on stage! What could go wrong?!

For decades, fully automated “lights-out” warehouses have captured our imagination, but the reality remained out of reach. Recent advances in robotics and AI are changing that, making lights-out execution viable in specific workflows and environments.

Progress will be incremental. Today, the most effective approach is hybrid: robots handle the bulk of repetitive work, while humans step in only when needed. This model already supports partial lights-out operations—such as running an unsupervised night shift while managing peak volumes and exceptions during the day.

The challenge is not just technical, but economic. Automating the final 10–20% of workflows, where edge cases and judgment calls live, is disproportionately complex and costly. Smart operators focus automation where ROI is strongest, preserve human flexibility where it adds the most value, and steadily reduce the exception set as technology and economics improve.

In this session, Brightpick CEO Jan Zizka outlines a practical roadmap to lights-out warehouse operations: where it works today, how to expand it safely and profitably, and what it takes to go fully lights-out.

We introduce the technology for generating simulation-ready (sim-ready) assets using Trinix, NdotLight's Text/Image-to-3D CAD solution. We will demonstrate how this technology goes beyond simple geometry creation to produce articulated objects with complex joint structures, while incorporating essential physical properties. Furthermore, we will share real-world use cases of these assets in Digital Twin and Physical AI.

Even the most advanced robotics teams hit a wall—not because of design, but because the development system around it is fragmented. Disconnected workflows between industrial design, product development engineering, sourcing, prototyping to scale manufacturing lead to late-stage performance, cost overruns, DFM issues, and supply chain delays, forcing teams to miss goals in time to market, product cost instead of strategic, proactive planning.

This session explores a new model: full-lifecycle integration for robotics development that gives teams support across ideation, industrial design, mechanical engineering, systems integration and supply chain development,   Development of the entire ecosystem —incorporating DFM and cost considerations from day one to ensure decisions are grounded in production reality.

Attendees will leave with a blueprint for closing the gap between design and deployment, learning how AI and integrated workflows transform robotics development from reactive into a seamless, predictive engine for innovation.

For more than a decade, Ghost Robotics has operated legged robots in mission-critical applications across defense, security, and industrial environments. Join Gavin Kenneally, CEO and co-founder of Ghost Robotics, as he shares lessons from 10 years of deploying quadruped robots in the field. The talk will cover real-world case studies, how advances in software are unlocking new capabilities, and what the next five years may hold for legged robotics in both the public and private sectors.

Robotics innovation depends on more than breakthrough ideas - it requires an ecosystem that can move seamlessly from engineering and design to manufacturing and operational scale. This panel explores how Hawk Ridge Systems, Stratasys, and Markforged collectively enable that transformation for robotics companies. By combining advanced engineering and design solutions, industrial additive manufacturing, and real-time manufacturing software, these organizations help robotics innovators shorten development timelines, improve manufacturing agility, and build a more resilient path to scale. For the robotics industry, this collaboration is especially relevant as companies face growing pressure to prototype faster, customize more efficiently, and transition into repeatable production with greater speed, visibility, and confidence.

Robots have been supporting hospital operations for years, from surgery and rehabilitation to logistics. Many people are familiar with how robotic systems have reshaped surgery and improved patient outcomes. Less visible, but equally important, are the robots that keep hospitals running efficiently behind the scenes. Over the past decade, SKA Robotics has supported the healthcare industry across a range of applications, including hospital logistics robots, surgical systems, prosthetics, and handheld medical devices.

Join us for the 3rd annual RBR50 Gala, a celebration of the world’s leading robotics innovators. The evening will honor winners of Robot of the Year, Startup of the Year, Application of the Year, Robots for Good winners and more. Guests will enjoy dinner, drinks, and an exclusive conversation with Steve Crowe, Chair of the Robotics Summit & Executive Editor of The Robot Report, Aaron Parness, Director of Applied Sciences at Amazon Robotics, and Bhavana Chandrashekhar, Senior Manager of Applied Science at Amazon Robotics. The conversation will explore Amazon’s latest robot, Vulcan — named RBR50 Robot of the Year — and the keys to its development and rollout. Attendance is limited to RBR50 ticket holders. Gala access can be added during Robotics Summit registration.