Imagine having a continuum soft robotic arm bend around a bunch of grapes or broccoli, adjusting its grip in real time because it lifts the item. Unlike traditional rigid robots that generally aim to avoid contact with the environment as much as possible and stay far-off from humans for safety reasons, this arm senses subtle forces, stretching and flexing in ways in which mimic more of the compliance of a human hand. Its every motion is calculated to avoid excessive force while achieving the duty efficiently. In MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and Laboratory for Information and Decisions Systems (LIDS) labs, these seemingly easy movements are the culmination of complex mathematics, careful engineering, and a vision for robots that may safely interact with humans and delicate objects.
Soft robots, with their deformable bodies, promise a future where machines move more seamlessly alongside people, assist in caregiving, or handle delicate items in industrial settings. Yet that very flexibility makes them difficult to manage. Small bends or twists can produce unpredictable forces, raising the chance of harm or injury. This motivates the necessity for protected control strategies for soft robots.
“Inspired by advances in protected control and formal methods for rigid robots, we aim to adapt these ideas to soft robotics — modeling their complex behavior and embracing, reasonably than avoiding, contact — to enable higher-performance designs (e.g., greater payload and precision) without sacrificing safety or embodied intelligence,” says lead senior writer and MIT Assistant Professor Gioele Zardini, who’s a principal investigator in LIDS and the Department of Civil and Environmental Engineering, and an affiliate faculty with the Institute for Data, Systems, and Society (IDSS). “This vision is shared by recent and parallel work from other groups.”
Safety first
The team developed a brand new framework that blends nonlinear control theory (controlling systems that involve highly complex dynamics) with advanced physical modeling techniques and efficient real-time optimization to provide what they call “contact-aware safety.” At the guts of the approach are high-order control barrier functions (HOCBFs) and high-order control Lyapunov functions (HOCLFs). HOCBFs define protected operating boundaries, ensuring the robot doesn’t exert unsafe forces. HOCLFs guide the robot efficiently toward its task objectives, balancing safety with performance.
“Essentially, we’re teaching the robot to know its own limits when interacting with the environment while still achieving its goals,” says MIT Department of Mechanical Engineering PhD student Kiwan Wong, the lead writer of a brand new paper describing the framework. “The approach involves some complex derivation of sentimental robot dynamics, contact models, and control constraints, however the specification of control objectives and safety barriers is reasonably straightforward for the practitioner, and the outcomes are very tangible, as you see the robot moving easily, reacting to contact, and never causing unsafe situations.”
“Compared with traditional kinematic CBFs — where forward-invariant protected sets are hard to specify — the HOCBF framework simplifies barrier design, and its optimization formulation accounts for system dynamics (e.g., inertia), ensuring the soft robot stops early enough to avoid unsafe contact forces,” says Worcester Polytechnic Institute Assistant Professor and former CSAIL postdoc Wei Xiao.
“Since soft robots emerged, the sphere has highlighted their embodied intelligence and greater inherent safety relative to rigid robots, because of passive material and structural compliance. Yet their “cognitive” intelligence — especially safety systems — has lagged behind that of rigid serial-link manipulators,” says co-lead writer Maximilian Stölzle, a research intern at Disney Research and formerly a Delft University of Technology PhD student and visiting researcher at MIT LIDS and CSAIL. “This work helps close that gap by adapting proven algorithms to soft robots and tailoring them for protected contact and soft-continuum dynamics.”
The LIDS and CSAIL team tested the system on a series of experiments designed to challenge the robot’s safety and adaptableness. In a single test, the arm pressed gently against a compliant surface, maintaining a precise force without overshooting. In one other, it traced the contours of a curved object, adjusting its grip to avoid slippage. In yet one more demonstration, the robot manipulated fragile items alongside a human operator, reacting in real time to unexpected nudges or shifts. “These experiments show that our framework is capable of generalize to diverse tasks and objectives, and the robot can sense, adapt, and act in complex scenarios while at all times respecting clearly defined safety limits,” says Zardini.
Soft robots with contact-aware safety could possibly be an actual value-add in high-stakes places, after all. In health care, they might assist in surgeries, providing precise manipulation while reducing risk to patients. In industry, they could handle fragile goods without constant supervision. In domestic settings, robots could help with chores or caregiving tasks, interacting safely with children or the elderly — a key step toward making soft robots reliable partners in real-world environments.
“Soft robots have incredible potential,” says co-lead senior writer Daniela Rus, director of CSAIL and a professor within the Department of Electrical Engineering and Computer Science. “But ensuring safety and encoding motion tasks via relatively easy objectives has at all times been a central challenge. We desired to create a system where the robot can remain flexible and responsive while mathematically guaranteeing it won’t exceed protected force limits.”
Combining soft robot models, differentiable simulation, and control theory
Underlying the control strategy is a differentiable implementation of something called the Piecewise Cosserat-Segment (PCS) dynamics model, which predicts how a soft robot deforms and where forces accumulate. This model allows the system to anticipate how the robot’s body will reply to actuation and sophisticated interactions with the environment. “The aspect that I most like about this work is the mix of integration of recent and old tools coming from different fields like advanced soft robot models, differentiable simulation, Lyapunov theory, convex optimization, and injury-severity–based safety constraints. All of that is nicely blended right into a real-time controller fully grounded in first principles,” says co-author Cosimo Della Santina, who’s an associate professor at Delft University of Technology.
Complementing that is the Differentiable Conservative Separating Axis Theorem (DCSAT), which estimates distances between the soft robot and obstacles within the environment that may be approximated with a sequence of convex polygons in a differentiable manner. “Earlier differentiable distance metrics for convex polygons either couldn’t compute penetration depth — essential for estimating contact forces — or yielded non-conservative estimates that might compromise safety,” says Wong. “As an alternative, the DCSAT metric returns strictly conservative, and subsequently protected, estimates while concurrently allowing for fast and differentiable computation.” Together, PCS and DCSAT give the robot a predictive sense of its environment for more proactive, protected interactions.
Looking ahead, the team plans to increase their methods to three-dimensional soft robots and explore integration with learning-based strategies. By combining contact-aware safety with adaptive learning, soft robots could handle much more complex, unpredictable environments.
“That is what makes our work exciting,” says Rus. “You may see the robot behaving in a human-like, careful manner, but behind that grace is a rigorous control framework ensuring it never oversteps its bounds.”
“Soft robots are generally safer to interact with than rigid-bodied robots by design, on account of the compliance and energy-absorbing properties of their bodies,” says University of Michigan Assistant Professor Daniel Bruder, who wasn’t involved within the research. “Nevertheless, as soft robots change into faster, stronger, and more capable, that will now not be enough to make sure safety. This work takes a vital step towards ensuring soft robots can operate safely by offering a technique to limit contact forces across their entire bodies.”
The team’s work was supported, partially, by The Hong Kong Jockey Club Scholarships, the European Union’s Horizon Europe Program, Cultuurfonds Wetenschapsbeurzen, and the Rudge (1948) and Nancy Allen Chair. Their work was published earlier this month within the Institute of Electrical and Electronics Engineers’ .
