---
title: Spline-Based Trajectory Representation
url: https://www.emergentmind.com/topics/spline-based-trajectory-representation
type: topic
---

# Spline-Based Trajectory Representation

A spline-based trajectory representation models the time evolution of systems, motions, or signals using spline functions—piecewise polynomial curves parameterized by control points and knot vectors. In fields as diverse as robotics, vision, autonomous systems, optimal control, machine learning, and computational biology, spline models facilitate highly smooth, continuous, and differentiable trajectory representations. Each trajectory's smoothness, local/global support, and constraint satisfaction are dictated by the specific type and degree of spline, with B-splines, Hermite splines, and Bézier splines being predominant choices. This technical overview examines the formulation, theoretical guarantees, optimization strategies, key computational properties, and state-of-the-art practical applications of spline-based trajectory representations.

## 1. Mathematical Foundations of Spline-Based Trajectory Models

Splines are parameterized by control points and defined over a nondecreasing knot sequence. For a $p$-th degree B-spline, the standard form is:

$$
x(t) = \sum_{i=0}^n P_i\,N_{i,p}(t)
$$

where $P_i$ are control points in $\mathbb{R}^d$ (or on a manifold), and $N_{i,p}(t)$ are the Cox–de Boor basis functions determined recursively:

\[
N_{i,0}(t) = 
  \begin{cases} 
    1 & u_i \le t < u_{i+1} \\
    0 & \text{otherwise}
  \end{cases}
\]
\[
N_{i,p}(t) =
  \frac{t-u_i}{u_{i+p}-u_i}\,N_{i,p-1}(t) +
  \frac{u_{i+p+1}-t}{u_{i+p+1}-u_{i+1}}\,N_{i+1,p-1}(t)
\]

Uniform splines use equally spaced knots. Continuity of order $C^{p-1}$ at every knot and $C^\infty$ inside spans is intrinsic to the construction [2212.10500][1904.12348][2402.00399]. Common alternatives include Hermite splines—in which the curve is parameterized directly by knot values and derivatives—with similar piecewise-polynomial form but explicit derivative boundary conditions [2511.10822][2606.07386]. Bézier splines use parameterized Bernstein polynomials and control polygons, which are structurally equivalent over each interval to a B-spline of the same degree.

Key higher-order properties:

- **Differentiability:** $k$-th derivatives of a degree-$p$ B-spline are themselves $(p-k)$-degree splines with explicitly computable control points.
- **Convex hull property:** At any $t$, $x(t)$ lies within the convex hull of the $p+1$ relevant control points. This is exploited for fast constraint satisfaction in velocity, acceleration, and for collision checking [1904.12348][2212.10500][2010.09904][2602.16758].
- **Manifold-valued splines:** Composite de Casteljau or log-exp mapping allows intrinsic spline curves on Riemannian manifolds, e.g., for pose trajectories in $SO(3)$ or $SE(3)$ [1911.08860][2303.17299][1805.02543][2402.00399].

## 2. Theoretical Guarantees and Constraint Satisfaction

Spline-based representations account for physical, kinematic, and environmental constraints at the analytic level:

- **Continuity and boundary conditions:** By design, splines enforce smoothness of the represented trajectory. For B-splines, $C^{p-1}$ continuity follows directly; for Hermite and Bézier splines, boundary and derivative constraint equations are imposed at segment joins [2606.07386][2511.10822][1904.12348].
- **Constraint reduction via convex hulls:** Due to nonnegativity and partition of unity, enforcing box or linear constraints at each control point suffices to guarantee satisfaction for all $t$ within the spline domain [2212.10500][2310.03359].
- **Collision avoidance:** For static obstacles, signed distance or separation constraints are imposed at the control points via the convex hull property. For dynamic obstacles, time-dependent separating hyperplane strategies, receding-horizon distance fields, or continuous-time surrogate cost terms (e.g., barrier functions or hinge losses) are used [2212.10500][2209.07003][2010.09904][2603.00759][1904.12348].
- **Dynamic feasibility:** Velocity, acceleration, and jerk limits can be checked at the derivative control points (or tight Bézier hulls). This guarantees global physical safety [1904.12348][2511.10822][2310.03359].

## 3. Optimization and Computational Properties

Major optimization paradigms for spline parameter (control point and time) selection include:

| Approach                   | Main Features                                                | References           |
|----------------------------|-------------------------------------------------------------|----------------------|
| Quadratic programming (QP) | Minimum snap/jerk, linear equality/inequality constraints   | [2105.01788]         |
| Nonlinear program (NLP)    | Time allocation, obstacle constraints, complex costs         | [2310.03359][2010.09904][2511.10822] |
| Graph search/Kinodynamic   | Discrete control-point search with feasibility checks        | [1904.12348]         |
| Gradient-based             | Real-time unconstrained or soft-constrained optimization    | [2209.07003][2212.10500][2504.06404] |
| Recursive subdivision      | Adaptive spatial refinement with convex hull tests           | [2010.09904]         |
| Analytic shaping           | Closed-form spline coefficients for fixed/flexible end data  | [2201.00101][2602.16758] |

- **Computational complexity:** For fixed-order splines and sparse constraints, QP-based approaches can achieve linear or near-linear scaling in the number of segments [2105.01788]. Block-banded sparsity arises from local support, facilitating efficient Gauss–Newton or direct solvers [2402.00399]. Recursive analytic formulas for derivatives and Jacobians yield $O(k)$ per-step evaluation on Lie groups [1911.08860].
- **Adaptive refinement:** Subdivision/refinement is applied locally where collision or constraint margins are tight, maintaining feasibility while enabling efficient global optimization [2010.09904].

## 4. Trajectory Representation in Diverse Domains

Spline-based trajectory models are central in a range of applications:

- **Robotic motion planning:** Multi-joint and Cartesian splines are used for minimum-time or minimum-jerk planning, with both soft and hard constraint enforcement. Advanced planners such as MIGHTY utilize Hermite quintic splines with collocation on Bernstein bases for efficient, unconstrained nonlinear optimization [2511.10822][2212.10500].
- **Quadrotor and differentially flat systems:** Flat outputs are parameterized as splines; minimum-snap/jerk is computed via QP/NLP techniques. Graph search over B-spline control points allows online replanning [1904.12348][2105.01788].
- **Autonomous vehicles:** Time-scaling, shrinkable horizon, and sparse spline bases provide time-optimal planning with continuous-time feasibility and collision avoidance [2310.03359].
- **Dynamic scene reconstruction and neural fields:** Hermite or B-spline based trajectory fields regularize spatial-temporal coherence, allow analytic kinematic calculation, and outperform implicit MLP-based fields in both spatial fidelity and motion realism [2507.07521].
- **Manifold-valued trajectories in geometry and vision:** Cumulative and composite B-splines are used for pose trajectories over $SO(3)$, $SE(3)$ with analytic derivatives, facilitating smooth visual-inertial fusion and state estimation [1911.08860][1805.02543][2402.00399].
- **Deep learning and sequence modeling:** Latent space trajectories can be encoded by continuous spline curves, as in Spline-based Transformers, yielding compact, smooth representations and enabling interpretable, continuous manipulation in neural models [2504.02797][2606.07386].
- **Computational biology:** In Wasserstein space, spline interpolation via barycentric optimal transport (“Wasserstein Lane–Riesenfeld subdivision”) reconstructs continuous stochastic processes from population snapshot data [2405.19679].

## 5. Extensions: Time Parametrization, Hybrid and Manifold Spline Models

- **Non-uniform and adaptive knots:** Time allocation and interval sizes can be treated as optimization variables, allowing knot-removal, dynamic resampling, and receding-horizon adaptation [2310.03359][2511.10822][2504.06404].
- **Higher-dimensional and hybrid trajectories:** Simultaneous position–orientation interpolation is achieved via hybrid position (B-spline) and orientation (quaternion-B-spline) approaches, with synchronization via arc-length parameterization and robust SLERP/Bézier-curve strategies [2602.16758].
- **Manifold splines:** For $SE(3)$, composite or cumulative B-splines perform Lie-algebraic interpolation, maintaining global consistency, analytic derivative recurrence, and preserving geometric structure [1911.08860][1805.02543][2402.00399][2303.17299]. In Wasserstein space, barycentric averages replace linear combinations, with convergence guarantees [2405.19679].
- **Physical consistency and data denoising:** Spline representations can be constructed (e.g., by integration of order-1 “radial” B-splines) to enforce strict kinematic consistency between position, velocity, and acceleration, even in the presence of missing or noisy data, forming the basis for robust trajectory filtering [2504.06404].

## 6. Benchmarking and Empirical Performance

Spline-based representations are empirically validated across domains. Highlights include:

| Task/Domain                    | Spline Form                | Performance Highlights                            | References              |
|--------------------------------|----------------------------|---------------------------------------------------|-------------------------|
| Robotic motion planning        | Quintic Hermite/Bézier     | 100% success rate, smooth locally optimal paths   | [2511.10822]            |
| Quadrotor minimum-snap         | Polynomial/B-spline        | Real-time replanning, 75ms solve for 5–10 spans   | [1904.12348][2105.01788]|
| Manipulation policy learning   | Piecewise quadratic spline | 40–50% reduction in forward-pass FLOPs, smoother action profiles | [2606.07386]            |
| Vision-based UAV navigation    | Cubic B-spline             | 80–120Hz online re-optimization, safe dynamic avoidance | [2209.07003]            |
| Structure from motion (SLAM)   | Cubic B-spline ($SO(3)$)   | Faster convergence, $\approx$2× speedup over $SE(3)$, analytic derivatives | [1911.08860][1805.02543]|
| Wasserstein barycentric inference| B-spline subdivision     | State-of-the-art held-out interpolation error, moderate runtime | [2405.19679]            |

In most technical benchmarks, spline models achieve higher trajectory smoothness (lower jerk/accel), stronger constraint satisfaction, and superior or equivalent task success rates versus grid-based, discretized, or black-box neural models.

## 7. Contemporary Trends and Future Directions

Current and emerging directions include:

- **Real-time and adaptive computation:** Efficient analytic recurrence, explicit Jacobians, and analytic time-allocation methods enable real-time, high-dimensional applications in robotics and SLAM [1911.08860][2511.10822][2603.00759].
- **Learning and uncertainty quantification:** Spline parameterization in policy networks allows compact latent spaces and closed-form uncertainty propagation throughout the action sequence and downstream controllers [2606.07386][2504.02797].
- **Constraint handling and exact feasibility:** Adaptive subdivision and convex-hull constraint reduction guarantee exact collision-free, physically valid trajectories throughout the optimization [2010.09904][2511.10822].
- **Manifold and distribution-valued interpolation:** Generalizations to Wasserstein and Riemannian settings extend the utility to cell biology, hurricane tracking, and broader geometric time-series analysis [2303.17299][2405.19679].
- **Hybrid symbolic-neural formulations:** Incorporation of spline experts into neural architectures yields models that combine smooth, controllable trajectories with data-driven flexibility.

## References

- [1904.12348] Real-time Trajectory Generation for Quadrotors using B-spline based Non-uniform Kinodynamic Search
- [2105.01788] Fast Spline Trajectory Planning: Minimum Snap and Beyond
- [2511.10822] MIGHTY: Hermite Spline-based Efficient Trajectory Planning
- [2212.10500] Continuous Trajectory Optimization via B-splines for Multi-jointed Robotic Systems
- [2310.03359] Time-Optimal Trajectory Planning in Highway Scenarios using Basis-Spline Parameterization
- [2602.16758] Smooth trajectory generation and hybrid B-splines-Quaternions based tool path interpolation for a 3T1R parallel kinematic milling robot
- [2402.00399] Continuous-time Trajectory Estimation: A Comparative Study Between Gaussian Process and Spline-based Approaches
- [2606.07386] Spline Policy: A Structured Representation for Robot Policies
- [1911.08860] Efficient Derivative Computation for Cumulative B-Splines on Lie Groups
- [2603.00759] Online Generation of Collision-Free Trajectories in Dynamic Environments
- [2010.09904] Robust & Asymptotically Locally Optimal UAV-Trajectory Generation Based on Spline Subdivision
- [2507.07521] Spline Deformation Field
- [2504.02797] Spline-based Transformers
- [2303.17299] Sasaki Metric for Spline Models of Manifold-Valued Trajectories
- [2405.19679] Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging
- [2201.00101] Analytical Shaping Method for Low-Thrust Rendezvous Trajectory Using Cubic Spline Functions
- [2504.06404] Physical spline for denoising object trajectory data by combining splines, ML feature regression and model knowledge
- [2209.07003] Vision-aided UAV navigation and dynamic obstacle avoidance using gradient-based B-spline trajectory optimization
- [1805.02543] Trajectory Representation and Landmark Projection for Continuous-Time Structure from Motion

Source: https://www.emergentmind.com/topics/spline-based-trajectory-representation