Resolver intelligently simulates and tests robot path and sequencing options in the cloud, delivering optimized, collision-free motion plans and interlock signals in minutes instead of months. The platform empowers manufacturers to reduce engineering effort by up to 50%, minimize cycle times, and dramatically improve throughput, without the usual trial-and-error bottlenecks.

To explore the impact of this breakthrough and how it’s being received by the automation community, we sat down with Ville Lehtonen, VP of Product at Realtime Robotics, for a deeper look into Resolver’s capabilities, the problems it solves, and what lies ahead for cloud-powered robotic simulation.

Ville brings over 17 years of robotics experience across Life Sciences, Logistics, and Manufacturing. He contributed to automation innovation in Life Sciences at LabMinds and HighRes Biosolutions. In Logistics, he led product efforts at Pickle Robot, scaling AI-powered unloading systems into commercial deployment. He has recently focused on real-time motion planning and adaptive control for high-mix manufacturing environments. Ville holds graduate degrees from both Oxford University and Aalto University, with a background that spans business and computer science. Originally from Finland, he now resides in Boston, MA.

1. How does Resolver redefine the traditional robot path planning process, and what makes it a game-changer for manufacturing?

Resolver doesn’t just make path planning faster; it fundamentally shifts its position in the process. Traditionally, path planning happens late in the game, after most design decisions are locked in. It’s slow, manual, and often based on assumptions that don’t hold up under real-world constraints.

Resolver flips that model. It plans the entire cell at once – task allocation, sequencing, interlocks – all of it. Because it runs in parallel, you can test multiple robot positions and EOAT configurations with almost no overhead. And it doesn’t just tell you if something works, it shows you what works best. It’s not ‘can I reach the target?’ but ‘what setup hits my cycle time target with margin?

The ability to get real answers fast and early changes how people approach system design. Users no longer need to commit to every decision up front. Ten ideas can be explored in parallel, and teams can move forward with data, not guesswork. That’s a significant shift, especially for those used to spending weeks just to validate a single layout.

So yes, it’s a better path planner. But more than that, it turns path planning into a lever for speed, iteration, and design freedom. It reduces effort, but more critically, it has the potential to save tremendous lead time.

2. How does cloud-based simulation improve robotic workcell design, and how does Resolver leverage this to reduce engineering effort by 50%?

Resolver drives a dramatic shift in workflow. Early access users reported a 50% reduction in engineering effort. Still, more recent data suggests this can be as high as 90% for certain cells, particularly those with complex layouts or frequent design changes.

A big part of this comes from the core path planning itself. What used to take days or weeks of manual programming, often requiring expert tuning and collision avoidance tweaking, can now be generated automatically in hours. That alone is a massive saving of effort and time.

Resolver’s cloud-based architecture also adds another layer of impact:

• Lead time: Because everything runs parallel on powerful cloud servers, entire workcells – or complete lines – can be validated overnight. That’s impossible when you’re limited by human resources or desktop simulation.
• Workload: In iterative tasks like EOAT selection, fixture design, or robot placement, teams typically get stuck waiting on upstream decisions. Worse, engineers lose momentum when constantly pulled into firefighting for other teams. Resolver removes much of that friction; multiple configurations can be tested in parallel, and the system returns not just ‘viable’ paths, but optimized ones.

So while path planning is the obvious efficiency win, the bigger story is how cloud-native parallelism clears bottlenecks between teams. That’s where the full 50-90% reduction in engineering effort comes from.

3. Resolver claims to reduce months of manual robot programming to just days or even hours. Can you walk us through a real-world example?

The power of Resolver isn’t just in speeding up path planning – it’s in how it transforms the entire simulation and deployment process.

Traditionally, simulation engineers spend weeks answering foundational design questions: How many robots do we need? Can the weld gun reach all targets without collisions? Will the fixture and EOAT combination hold up? These aren’t just technical issues; they define cycle time, capital cost, and production feasibility. Resolving them manually is slow and expertise-heavy.

Resolver flips that process. It acts like a virtual simulation engineer, evaluating robot positioning, tooling choices, path feasibility, and interlocks, and does so all at once, across the entire cell. And it doesn’t just say ‘this works’; it highlights which setup delivers better cycle time, higher utilization, or fewer risks. That kind of insight improves decisions from day one.

After using Resolver across a few workcells, one customer said they realized they could feasibly load every cell of a large project into the system on day one – and then have optimized robot positions, EOAT choices, and full paths by day two. That hasn’t happened yet, but the recognition was clear: the bottleneck is no longer the software; it’s just whether the team chooses to operate that way.

Fixture design is still a separate workflow, but we’re seeing early interest from partners building generative AI tools that could co-design fixtures to match Resolver’s output. If that matures, fixture iteration could even be automated and validated overnight.

In short, customers are starting to rethink what the first week of a project could look like. That shift—fueled by Resolver—could compress months of work into just a few days—not through heroics but by changing the starting line.

4. What differentiates Resolver from existing robotic simulation and optimization tools, especially in handling multi-robot systems and collision avoidance?

Resolver fundamentally differs from traditional robot simulation and optimization tools because it doesn’t solve for one robot at a time. It plans the entire workcell holistically, including task allocation, sequencing, and interlocks, across all robots. That’s the structural shift. Once you’re solving globally, you simply unlock results that aren’t possible with single-robot, sequential planning approaches.

There are a few key differentiators:

• True multi-robot planning: Resolver can handle 10, 15, or 20 robots in a single cell.
• Automatic interlock handling: Customers often tell us that Resolver is the first tool they’ve used where the robots don’t crash. That’s not magic; it’s baked into how we solve the problem.
• Sequence and allocation optimization: We don’t just find valid paths; we decide which robot should do which task, and in what order, to hit cycle time targets.
• Faster path planning: When benchmarking against a major simulation tool, one customer saw Resolver produce 20% faster plans—even in relatively simple cells.
• Cloud-native architecture: Resolver runs in parallel on scalable cloud resources, which means a user can validate a full line overnight and come back with real answers.

Resolver comparisonPut simply, Resolver isn’t a path planner with extra features—it’s a completely different model for planning, optimizing, and validating robotic cells.

5. How can small and medium manufacturers leverage Resolver to stay competitive, especially when they lack the deep engineering resources of larger enterprises?

Resolver is especially valuable for small and mid-sized manufacturers because it removes the need for one of the most brittle roles in automation: path planning. The problem isn’t just that path planning is specialized; it’s that it’s single-purpose. You might need ten hours of it one week, then nothing for a month. Compare that to CAD skills, broadly applicable across design, engineering, and manufacturing tasks.

This mismatch creates real overhead. Hiring a full-time path planner doesn’t make sense unless you’re running at a serious scale. But relying on an integrator whenever you need a change slows you down and eats into margins. And if you do hire someone, how do you know for sure that they’re good? What happens when they quit?

Resolver changes the equation. It gives organizations access to high-end planning capabilities without having to build a fragile in-house function or tie themselves to long-term contracts. More importantly, it lets you stay flexible. You don’t have to treat automation as a static thing just to make the economics work. You can adapt on the fly, without breaking the bank.

That’s how smaller manufacturers stay agile and competitive.

6. What’s next for Resolver—are there any upcoming integrations, AI enhancements, or features that will further empower robotic automation in Industry 4.0 environments?

The only integration we can publicly confirm right now is with Visual Components, which we’re launching at Automatica 2025. Several other integration projects are underway, but since they involve close collaboration with partners, we’ll coordinate announcements together with them. Longer term, you can expect integrations with more sophisticated 3D simulation platforms and even CAD tools to support early-phase design.

As for the product roadmap, we’re focused on three major pushes: some very AI-driven, others more standards- and rules-based. These include:

• Design-enabling tools: Think automatic robot positioning, EOAT selection, robot choice, and fixture design support. These are heavy on AI and aim to reduce the up-front work required to scope and build an automated cell.
• OEM standard adherence: For applications where robot motion needs to follow strict OEM guidelines, we’re building support to generate paths that align with those standards – no AI needed, just precision and correctness.
• Line-level tools: This includes features like line balancing, robot and EOAT allocation across multiple stations, and reachability validation at production scale. These will be deeply AI-enabled and cloud-powered.

The long-term vision is simple: customers bring the process they want to execute, and Resolver handles everything else. With a solid digital twin in place, this kind of full-stack automation isn’t theoretical – it’s within reach.

The post A conversation with Realtime Robotics’ Ville Lehtonen on the launch of Resolver and collision-free robot motion planning appeared first on RoboticsBiz.

The Importance of Intelligent Automation

Intelligent automation is essential for modern enterprises as it enhances efficiency, accuracy, customer experience, adaptability, and cost savings. Here are some key reasons why IA is vital:

• Increased Efficiency and Productivity: IA automates repetitive and time-consuming tasks, enabling employees to focus on strategic and value-added activities. Streamlined processes and fewer manual interventions lead to improved operational efficiency and productivity.
• Improved Accuracy and Quality: By following predefined rules and standards, IA reduces human error, ensuring consistent and accurate task execution. This minimizes data entry mistakes and process deviations, improving data quality and reducing rework.
• Enhanced Customer Experience: IA optimizes customer-facing processes, ensuring faster response times, reduced wait times, and consistent, personalized interactions. This leads to increased customer satisfaction and loyalty.
• Agility and Adaptability: IA’s cognitive capabilities allow systems to adapt to changing circumstances and handle complex tasks. These systems can learn from data patterns, make intelligent decisions, and quickly respond to market changes, customer demands, and regulatory requirements.
• Cost Savings: Automating manual and repetitive tasks reduces labor costs and improves operational efficiency. IA minimizes the need for additional workforce and decreases human-related errors, leading to significant cost savings over time.
• Data Insights and Analytics: IA leverages AI and machine learning algorithms to analyze large volumes of data, extract valuable insights, identify trends, and provide data-driven recommendations for process optimization and decision-making.

Seven Leading Intelligent Automation Technologies

1. Structured Data Interaction (SDI)

SDI involves the integration of well-structured information through traditional systems such as relational databases (RDBMS), data transformation tools, application programming interfaces (APIs), and web services. This technology ensures seamless data exchange and integration across different systems.

2. Robotic Process Automation (RPA)

RPA automates standardized, rule-based tasks using scripts and other methods to support efficient business processes. It is ideal for tasks that are too expensive or inefficient for humans, evolving from isolated automation installations to comprehensive, enterprise-class digital automation solutions.

3. Machine Learning (ML)

ML systems learn by handling variations not anticipated upfront, training on data to make predictions or classifications. For example, ML can map a vendor name to its ID on an invoice, even if the name appears in different forms.

4. Natural Language Processing (NLP)

NLP uses statistical methods and algorithms to analyze text and unstructured information, understanding meaning, sentiment, and intent. In customer service, NLP analyzes support tickets to determine urgency and priority based on the customer’s emotions and frustrations.

5. Natural Language Generation (NLG)

NLG creates text from structured information, such as fields and numerals, to generate reports and insights. For example, NLG can generate sections of financial analysis reports based on a company’s performance data.

6. Chatbots and Virtual Agents

These systems interpret voice/text in free form with predefined answers, continually learning and building vocabulary to improve their responses. In customer service, chatbots can answer queries and provide support, enhancing the customer experience.

7. AI-Decision Systems

AI-decision systems use a range of technologies, algorithms, and models to solve complex decision-making issues. These systems, powered by deep learning and cognitive abilities, recognize patterns and apply statistical models to make informed decisions, such as predicting product demand based on weather forecasts.

Trends Shaping Intelligent Automation in 2024

As intelligent automation continues to evolve, several key trends are shaping its trajectory. These trends highlight the increasing sophistication, integration, and impact of IA technologies across various industries.

1. Deepening AI, RPA, and BPM Convergence

A significant trend is the convergence of artificial intelligence (AI), robotic process automation (RPA), and business process management (BPM) into unified platforms. According to new data from Forrester, 48 percent of organizations plan to integrate RPA and BPM into a single IA platform. This integration enables bots to perform more complex tasks, make data-driven decisions, and handle unstructured data. By combining AI with RPA, enterprises can move beyond simple rule-based automation to implement cognitive abilities, predictive modeling, and intelligent decision-making. This convergence allows businesses to optimize processes more effectively and enhance their overall operational efficiency.

2. Expansion into Non-Traditional Sectors

Intelligent automation is rapidly expanding into sectors that have traditionally relied on manual processes. Industries such as healthcare, legal, and education, which have been slow to adopt automation, are now embracing IA technologies to streamline operations. For example, in healthcare, many routine administrative tasks are still performed manually. Legislative changes and technological advancements are driving these industries to adopt intelligent process automation. This expansion allows businesses in these sectors to improve efficiency, reduce costs, and enhance service delivery.

3. Standardized and Ethical Automation Practices

As IA adoption grows, organizations are placing greater emphasis on governance, standardization, and ethical practices. Establishing RPA Centers of Excellence (CoEs) is becoming more common to manage and optimize automation programs effectively. These CoEs ensure consistency, security, and compliance across automation initiatives. Additionally, sustainability and environmental, social, and governance (ESG) reporting requirements are driving the need for ethical IA practices. Active digital workers minimize resource consumption, optimize business processes, and support data governance, promoting sustainability and ethical standards.

4. Internet of Things (IoT) Integration

The integration of the Internet of Things (IoT) with intelligent automation is creating a network of interconnected devices that communicate and share data in real-time. IoT enhances connectivity, data-driven decision-making, and remote management capabilities. By integrating IoT with IA, organizations can develop more streamlined and intelligent automated processes. For example, real-time sensor data from IoT devices can enable manufacturers and warehouse operators to make instant, data-driven decisions, improving operational efficiency and responsiveness.

5. Advanced NLP Technologies

Natural language processing (NLP) technologies are advancing, enabling bots to interpret and process human language more effectively. When combined with automation methods like RPA, NLP-powered bots can communicate with users using natural language, understand inquiries, provide support, and complete tasks based on user inputs. For instance, NLP can be used to monitor user feedback across multiple channels, perform sentiment analysis to gauge customer sentiment, and generate reports based on customer feedback. These capabilities improve automation by allowing bots to handle unstructured data, categorize information, and provide tailored customer support through chatbots or virtual assistants.

6. Augmented Intelligence

Augmented intelligence is an emerging trend where IA technologies enhance human decision-making rather than replacing it. This approach is particularly valuable for high-touch customer service needs that require human intuition and empathy. Augmented intelligence enables data scientists and other professionals to manage large amounts of structured and unstructured data while providing customers with personalized experiences that pure AI cannot always deliver. In this symbiotic relationship, humans make the final decisions while machines handle the data required for informed decision-making.

7. Hyperautomation

Hyperautomation goes beyond traditional RPA by using a wide range of automation tools and technologies to rapidly transform entire business processes. Hyperautomation aims to automate as many business and IT activities as possible, resulting in improved workflows, productivity, and decision-making. It involves not only automating workflows and process steps but also restructuring work to allow individuals to focus on more creative and strategic tasks. By leveraging technologies like AI, machine learning, and advanced analytics, hyperautomation enables organizations to achieve higher levels of efficiency and agility.

The post Top 7 intelligent automation technologies transforming enterprises appeared first on RoboticsBiz.

Below we explain the salient features that make RPA a force to reckon with.

What is unique about RPA?

Robotic Process Automation developed as an offshoot of Artificial Intelligence and is a software that automates business processes and optimizes legacy systems (old and outdated systems and applications). Kansas software developers at Tricension share that RPA’s uniqueness lies in giving you unified control over multiple processes along with scalability of operations. Using RPA, skilled technicians find it easier to accomplish complex tasks.

In layman’s terms, RPA is a software bot that mimics human action in addressing business processes.

RPA breaks down the most complex processes into sequential tasks to complete a project with minimum delay.

RPA automates processes and eliminates the need for human intervention in routine tasks, making skilled personnel more efficient and effective.

How does RPA optimize performance?

RPA works through “intelligent integration,” making it possible to harmonize legacy systems that defied integration. RPA makes you a virtual user interacting seamlessly across platforms with multiple applications and custom apps. You’ll be delivering packaged solutions regardless of whether you have or don’t have an API at your disposal. Essentially, RPA is a long-term structural solution when you’re handling different applications that are otherwise difficult to integrate.

Why are businesses keen on RPA?

With changing customer preferences and the multiplicity of demands continually being made by markets, businesses are struggling to stay relevant. 

There is an increasing focus on innovating new products, refining marketing strategies and boosting sales through customization. 

It’s challenging to do this when you’re grappling with distributed IT systems, running several operations wholly dependent on your workforce. It becomes an uphill task to change the IT infrastructure frequently to address complex issues while adhering to limited timeframes and manage to stay within the budget.

Your business goals become achievable when you reduce manual operations and automate tasks that do away with human intervention. Robotic automation helps you interact with existing IT infrastructure without making drastic changes to complex systems. Instead of replacing business applications, you are automating processes to improve efficiencies, and diverting skilled workforce where it is needed.

What are the stages of RPA implementation?

It is challenging to operate a growing business where human capital, overwhelmed by routine and repetitive tasks, becomes incapable of planning and strategizing the future. RPA solves many legacy headaches by systematically transferring specific human processes to bots. It is how RPA is implemented:

The planning stage

• An RPA checklist helps you identify the human processes that need automation by addressing core issues.
• Which aspect of your existing IT system needs to be changed? What should be retained? What must be rejected?
• Which processes are manual and can be automated to reduce the burden on employees?
• Is the volume of customer-centric data that you’re aggregating readable and accessible through a single interface?
• Do you have a rule-based system in place that gathers, sorts, archives, and manipulates data the way the business needs the data to be organized? 

Once you have identified the areas that need RPA processing, a trained and oriented project deployment team defines its approach and finalizes the schedule for implementation. Logging methods will be devised to locate and rectify bot-related errors.

The Bot development architecture

You can’t expect technology to function independently without giving it a direction and purpose. It is the stage where the RPA developer Team focuses exclusively on creating the right environment for the reengineered process to work.

Software updates and security patches are enabled to manage and maintain the bots efficiently. The general idea is to install a governance module that identifies and resolves issues quickly so that the system runs without glitches.

The Bot testing environment

It is widely accepted that testing is the gateway to detecting failure, and failure is the stepping stone to promote a better understanding of the way the system works. Even small variations in processes (for example, the way data is formatted) can impact bot results.

The modular design of RPA enables you to independently test various components and ensure bots are working as they ought to be working. Ideally, the developer, the reviewer, and the testing personnel should be independent entities that validate and implement the test plan.

How RPA benefits business process reengineering

In the business ecosystem, where entrepreneurs are wary of transformational change, RPA can accelerate business processes that stagnated over the decades. Reformed structures and revised processes will bring about a ten-fold leap across performance parameters. Let’s judge for ourselves how this transformation occurs.

• RPA builds a single customer interface providing all information necessary for gaining a unified customer view. 
• RPA increases the efficiency of operations, thereby improving employee productivity necessary for delivering better customer experience.
• RPA effectively eliminates manual errors, assuring higher quality data that lays the foundation for accurate analyses.
• More efficient processes help you stay ahead of the competition, leading to improved customer satisfaction.
• By using software bots to automate tasks, you achieve cost savings exceeding 30% by limiting expenditure on full-time employees.
• The time it takes to handle a call transaction (Average Handle Time/ Average Resolution Time) can be reduced substantially (by 80 to 90 percent). 

The sectors benefiting through RPA

Banking, Insurance, and Finance: Claims settlement, premium processing, auditing, and fraud detection.

Healthcare: Patient admission and discharge protocols, clinical data extraction terminals, patient history archiving, and retrieval.

Shipping and Logistics: Warehousing, transportation, and carrier tracking.

Ecommerce: Order-to-cash invoicing and credit collections with delivery tracking from source to destination.

Customer communication: Reinforcing customer loyalty through regular bot communication via email notifications conveying order specifications, shipping schedules, and delivery details.

Manufacturing and retail business: Procurement and inventory management, keyed into customer demand.

Government: Streamlining and validating voter identification, taxation, and licensing protocols.

Conclusion

RPA’s global acceptance rides on three crucial factors – the ability to cut costs, the optimization of resource mobilization, and the negation of errors, delivering automated bliss in our workspaces.

RPA is versatile because it moves beyond the limitations and restrictions imposed by outdated legacy systems. In the foreseeable future, we’ll see RPA combined with AI and the Internet of Things (IoT) revolutionizing business management processes.

Chatbots will enrich the conversational experience, and voice-enabled services will grow in stature and scope.

The ultimate beneficiary of the pathbreaking merger of RPA/ AI/ IoT will be the client receiving customized business solutions.

The post Understanding how RPA can automate business processes appeared first on RoboticsBiz.