- Atlas
- Engineering
- Robot Motion Planning
Robot Motion Planning
Robot motion planning is the part of robotics that decides where a robot should go: how to get an arm, a rover, or a drone from where it is to where it needs to be without hitting anything, and how to do so efficiently, safely, and in the face of a world that is only partly known.
7 frameworks, from 1978 to today · Robotics · Engineering
Overview
Robot motion planning is the part of robotics that decides where a robot should go: how to get an arm, a rover, or a drone from where it is to where it needs to be without hitting anything, and how to do so efficiently, safely, and in the face of a world that is only partly known1. It sits between perception (what the robot knows about the world) and control (how its motors execute a command). Its central object is the path or trajectory—a curve through space, possibly with timing and velocities attached—and its central difficulty is that the space of possible motions is enormous, while the obstacles inside it make the problem combinatorially hard1. Over roughly five decades the field has moved through geometric exactness, artificial forces, random sampling, numerical optimization, and, most recently, learning. Each turn answered a problem the previous one could not.
Configuration Space: Turning a Robot into a Point
The founding move of the field was a change of representation. In the late 1970s and early 1980s, Tomás Lozano-Pérez, working at MIT, formalized the idea of configuration space (often abbreviated C-space): the set of all possible positions of the robot, one coordinate per degree of freedom. A six-joint arm becomes a point in a six-dimensional space; a wheeled robot becomes a point in a three-dimensional one (two position coordinates plus heading)1. The robot's body is then "shrunk" to that point, and every obstacle is "grown" by the robot's shape into a C-obstacle. Planning becomes the problem of finding a curve from a start point to a goal point that avoids the grown obstacles1.
This was powerful because it converted a problem about a complicated physical body into a problem about a single point in a high-dimensional space. It also made the difficulty visible: the C-space of a real arm has six or more dimensions, and the grown obstacles can have intricate shapes. Lozano-Pérez's work, together with that of Rodney Brooks and others in the same period, established the geometric framing that still underlies almost everything that follows. Exact methods—cell decomposition, which chops free space into simple cells and searches a graph of them, and the visibility graph, which connects obstacle corners with straight lines—could solve low-dimensional problems completely1. But their cost grows explosively with dimension, and by the late 1980s it was clear that exact geometric planning would not scale to real arms and mobile robots.
Potential Fields and the Reactive Turn
A different answer came from physics rather than geometry. In the mid-1980s Oussama Khatib proposed artificial potential fields: treat the goal as an attractive force and obstacles as repulsive ones, and let the robot roll "downhill" toward the goal like a ball on a landscape. The appeal was speed and elegance—the robot needs only local information about nearby obstacles, and the method produces smooth motions in real time1. It became a foundation of real-time obstacle avoidance and influenced the force-control tradition in manipulation.
Its weakness is equally instructive. A potential field can trap the robot in a local minimum—a dip in the landscape that is not the goal, such as the pocket between two obstacles directly on the line to the target1. The robot stalls, convinced it has nowhere better to go. This failure, and the desire for robots that react to a changing world rather than execute a precomputed plan, fed the reactive and behavior-based current of the late 1980s and 1990s, associated above all with Rodney Brooks at MIT. Brooks argued that intelligence could emerge from layered reactive behaviors—"avoid obstacles," "wander," "follow"—without a central world model. For motion, this meant planners that continuously re-decide from sensor readings. The approach gave robots impressive real-time agility but no guarantee of reaching a goal in a cluttered environment, and the tension between guaranteed completeness and real-time reactivity became a defining theme.
Sampling: Randomness as a Strategy
The decisive break came in the late 1990s, when researchers stopped trying to describe free space exactly and instead sampled it. The key insight: in a high-dimensional C-space you cannot build the obstacles, but you can cheaply test whether a single configuration is collision-free1. So generate random configurations, keep the free ones, and connect nearby ones into a graph or tree1.
Two families emerged. Probabilistic roadmaps (PRMs), introduced by Lydia Kavraki and colleagues in the mid-1990s, build a reusable network of free-space samples once and then answer many start–goal queries on it—well suited to a fixed workspace such as a factory cell. Rapidly-exploring random trees (RRTs), introduced by Steven LaValle in the late 1990s, grow a tree outward from the start by repeatedly sampling a random target and extending toward it; the randomness makes the tree spread quickly into unexplored space. A widely used variant, RRT, later showed that with enough samples these trees converge toward optimal paths. Around the same time, the probabilistic completeness* guarantee was articulated: a sampling planner will find a path if one exists, with probability approaching one as sampling continues—a weaker but far more practical promise than exact completeness1.
Sampling planners made real, high-dimensional problems tractable for the first time: seven-degree-of-freedom arms in cluttered kitchens, humanoid robots, and mobile manipulators. They remain the workhorses of the field1. Their costs are also well known—paths are often jerky and far from optimal, and performance varies run to run—which set up the next turn.
Trajectory Optimization: Planning as a Numerical Problem
Where sampling treats planning as search, trajectory optimization treats it as continuous optimization: define a cost (say, effort, time, or smoothness), impose constraints (collision-free, within joint limits, obeying dynamics), and solve numerically for a whole trajectory at once2. The lineage runs through optimal control—the calculus-of-variations and dynamic-programming traditions of the mid-twentieth century—and through numerical optimal-control methods developed for aerospace and process engineering23. In robotics it matured in the 2000s and 2010s into methods that produce smooth, dynamically feasible, often near-optimal motions, and it is now the standard approach for legged locomotion, drone flight, and aggressive arm maneuvers.
The catch is that optimization finds local optima and is sensitive to its starting guess; a bad initialization can send the solver into a collision or a poor solution. In practice, the field often combines the two ideas: use a sampling planner to find a rough feasible path, then optimize it into a smooth trajectory. This hybrid—sometimes called "sample, then optimize"—is one of the most common patterns in modern motion planning.
Planning Under Uncertainty
All of the above assumes the robot knows where it is and where the obstacles are. Real robots do not. Planning under uncertainty asks how to act when positions, maps, and the effects of actions are only probabilistically known. The intellectual foundation is the partially observable Markov decision process (POMDP), a formal model in which the robot maintains a belief—a probability distribution over possible states—and chooses actions to reduce uncertainty and reach the goal4. Exact POMDP solutions are intractable for realistic problems, so the field developed approximations, and in mobile robotics the practical form became belief-space planning: plan over distributions rather than single states, so that the robot deliberately moves to gather information (for example, toward a landmark to localize itself) as well as toward its goal.
A parallel strand, developed in the 2000s and 2010s, is planning that explicitly accounts for collision probability and for the uncertainty of moving obstacles, producing paths that keep a safety margin rather than threading gaps that are only probably clear. This work connects motion planning tightly to probabilistic robotics and to the perception and SLAM traditions that estimate the robot's state5.
Learning to Plan
The most recent turn brings machine learning into the planner itself. Learning-based motion planning covers several distinct ideas. One is to learn a policy—a mapping from sensor input directly to motion—by reinforcement learning or imitation, so that the robot reacts without solving a planning problem online; this has produced impressive results in locomotion and in manipulation from raw images. Another is to learn to accelerate classical planners: neural networks trained to propose good samples, good heuristics, or good initial trajectories for sampling and optimization methods, cutting the time they need. A third is to learn models of dynamics or of collision from data, which planners then use.
The appeal is clear—learned planners can exploit patterns in the environment and run fast—but so are the open problems: guarantees of safety and completeness are hard to obtain, and learned policies can fail unpredictably outside their training distribution. Much current work tries to combine learned components with the formal guarantees of classical methods rather than replace them.
Where the Field Stands
Today the main approaches coexist and are routinely combined. Sampling-based planners (RRTs, PRMs and their variants) remain the default for high-dimensional, cluttered problems where completeness matters. Trajectory optimization supplies smooth, dynamically feasible motion and dominates legged and aerial robotics. Reactive and potential-field methods survive as fast local layers inside larger systems. Belief-space and chance-constrained planning handle uncertainty, and learning increasingly accelerates or replaces parts of the pipeline. The open questions are the old ones in new form: how to guarantee safety when the world is only partly known and the planner is partly learned; how to plan in real time for robots with many degrees of freedom in dynamic environments shared with people; and how to make the guarantees of classical planning survive contact with data-driven components. The history of the field is, in large part, a history of trading one kind of guarantee for another kind of capability—and then working to get the guarantee back.
References
- Motion planning (introduction, Concepts, Free space, Configuration space, Algorithms, Geometric algorithms, Artificial potential fields, Sampling-based algorithms, Completeness and performance), Wikipedia
- Trajectory optimization (introduction, History), Wikipedia
- Optimal control, Wikipedia
- Partially observable Markov decision process, Wikipedia
- Simultaneous localization and mapping, Wikipedia
The frameworks of Robot Motion Planning
Each framework is a way of working the field has used: when it held, and the question it answers.
- 1978-1995
Configuration Space Planning
How can a robot's motion be reduced to a point in a space?
- 1985-2000
Artificial Potential Fields
How can forces guide a robot around obstacles in real time?
- 1986-2000
Reactive planning
How can a robot react to its surroundings without a full plan?
- 1994-Present
Sampling-Based Planning
How can randomness make high-dimensional planning tractable?
- 1998-Present
Planning Under Uncertainty
How should a robot act when it does not know exactly where it is?
- 2000-Present
Trajectory Optimization
How can a whole trajectory be computed as an optimization problem?
- 2010-Present
Learning-Based Motion Planning
How can a robot learn to plan from experience?
How the ideas connect
Each arrow runs from an earlier idea to the later one it shaped. The list below says what passed between them.
Sampling-Based Planning influenced by Configuration Space Planning
Sampling-based planning inherited the configuration-space formulation: PRMs and RRTs sample configurations and test collision in C-space, and the probabilistic-completeness guarantee is stated over C-space connectivity. The C-space concept is the foundation on which sampling planners operate.
Carried by Lydia Kavraki; Steven LaValle; Tomás Lozano-Pérez.
Reactive planning reacted against Configuration Space Planning
Brooks's reactive and behavior-based robotics defined itself against the sense-model-plan-act pipeline that exact geometric planning exemplified, arguing that layered reactive behaviors could replace a central world model and precomputed plans. The reactive turn was a direct rejection of the deliberative planning paradigm built on configuration-space search.
Carried by Rodney Brooks.
Trajectory Optimization influenced by Sampling-Based Planning
Trajectory optimization methods commonly take a rough feasible path from a sampling planner as their initial guess, the 'sample, then optimize' pattern. Sampling provided the collision-free initialization that local optimization needs to avoid poor local optima.
Learning-Based Motion Planning influenced by Sampling-Based Planning
Learning-based planners often learn to propose good samples, heuristics, or initial trajectories for sampling planners, accelerating them. The sampling framework provided both the target of acceleration and the data-generation mechanism for training.
Learning-Based Motion Planning influenced by Trajectory Optimization
Learning-based planning learns policies or initial trajectories that replace or warm-start trajectory optimization, and learned dynamics models are used inside optimizers. Trajectory optimization supplied the cost-and-constraint formulation that learned components are trained to serve.
Planning Under Uncertainty influenced by Sampling-Based Planning
Planning under uncertainty extended sampling ideas to belief space, where planners sample or propagate distributions over states rather than single configurations. The sampling machinery developed for deterministic C-space planning was adapted to probabilistic settings.
Learning-Based Motion Planning influenced by Planning Under Uncertainty
Learning-based planners that map sensor input directly to motion inherit the belief-space idea of acting on probabilistic state estimates, and reinforcement learning is used to approximate policies for problems formulated as POMDPs. Planning under uncertainty provided the formal problem setting that learned policies approximate.
Beyond the field
Where Robot Motion Planning's ideas came from in other fields, and what they led to there: the strongest 12 of 37 links.
Configuration Space Planning led to Configuration Space Approach in Computational Geometry
The configuration-space approach to motion planning, formulated by Lozano-Pérez and Udupa in the late 1970s, is the direct ancestor of the configuration-space framework in robotics; the later framework generalises and formalises that planning formulation.
Carried by Tomás Lozano-Pérez.
Reactive planning reacted against Classical action representation and planning in Planning And Search
Reactive planning arose as a direct attack on classical symbolic planning, arguing that explicit world models and search over action representations were the wrong basis for robot control. Brooks's subsumption architecture was framed as a rejection of the STRIPS-style planning tradition.
Carried by Rodney Brooks.
Reactive planning reacted against Deliberative robotics in Mobile Robotics
Reactive planning defined itself by rejecting the deliberative sense-model-plan-act architecture of Shakey and its successors. Brooks argued that the world should serve as its own model rather than being represented and planned over.
Carried by Rodney Brooks.
Planning Under Uncertainty influenced by Markov decision process in Stochastic Modeling
The Markov decision process as a stochastic-modeling framework is the formal basis of planning under uncertainty, which solves MDPs and POMDPs for robot control. The stochastic-modeling formulation supplied the transition-probability model the planners optimize over.
Planning Under Uncertainty influenced by Markov decision process in Planning And Search
Planning under uncertainty is built directly on the Markov decision process formalism, extending it to partially observable settings via POMDPs. The MDP supplied the state, action, transition and reward structure that the planners use.
Trajectory Optimization influenced by Optimal control in Control Theory
Trajectory optimization for robots is a direct application of optimal control theory, using its cost functionals, dynamics constraints and numerical solvers. The optimal-control tradition supplied the entire problem formulation.
Trajectory Optimization influenced by Optimal control in Control Systems
Trajectory optimization in robotics draws on optimal control as developed in control systems engineering, including the numerical solution of constrained optimal-control problems. The control-systems formulation is the direct source of the robot methods.
Learning-Based Motion Planning influenced by Reinforcement learning for robot control in Robot Learning
Reinforcement learning for robot control is the direct source of the trial-and-error policy optimisation that learning-based motion planners use, with planners often trained by RL in simulation and transferred to real robots.
Learning-Based Motion Planning grew out of Robot learning in Robotics
Learning-based motion planning grew directly out of robot learning: the same community's methods for learning policies and models from robot experience were turned on the planning problem, with learned components replacing hand-designed planners or cost functions.
Configuration Space Planning influenced Probabilistic Manipulation under Uncertainty in Robot Manipulation
Configuration space planning provided the geometric representation of free space and the planning algorithms that probabilistic manipulation extends by treating configurations as uncertain random variables.
Carried by Tomás Lozano-Pérez.
Configuration Space Planning influenced by Manipulator kinematics and dynamics in Robotics
Configuration space planning took the manipulator's joint-space description and forward kinematics from manipulator kinematics and turned the robot's degrees of freedom into the planning space. Lozano-Pérez's 1979 configuration-space formulation is built directly on this kinematic description.
Carried by Tomás Lozano-Pérez.
Configuration Space Planning influenced Sense–Plan–Act Pipeline in Robot Manipulation
Configuration space planning supplied the planning stage of the pipeline, computing collision-free paths in configuration space from sensed models.
Carried by Tomás Lozano-Pérez.

Robot Motion Planning is a planet in Nousfarer
Its city has a tower for each of these 7 frameworks. Land, walk in, and climb one concept at a time.
Land on Robot Motion PlanningRelated fields
Fields its ideas are linked to
- Computational Geometry 6 links
- Planning And Search 4 links
- Robot Manipulation 4 links
- Robotics 4 links
- Robot Learning 3 links
- Mobile Robotics 2 links
- Multi Robot Systems 2 links
- Robot Kinematics Dynamics 2 links
- Reinforcement Learning 1 link
- Calculus Of Variations 1 link
- Control Theory 1 link
- Mathematical Optimization 1 link
More in Robotics
- Human Robot Interaction
- Mobile Robotics
- Multi Robot Systems
- Robot Control
- Robot Kinematics Dynamics
- Robot Learning
- Robot Manipulation
- Robot Perception And Slam
- Robotics
See where Robot Motion Planning sits on the Map of Human Knowledge